Papers by Mirella Lapata

Help Me Write a Story: Evaluating LLMs’ Ability to Generate Writing Feedback (2025.acl-long)

Challenge:	Existing approaches to summarize documents are not extractive and require an abstractive approach.
Approach:	They propose a novel abstractive model which is conditioned on the article’s topics and based entirely on convolutional neural networks.
Outcome:	The proposed model outperforms an oracle extractive system and state-of-the-art abstractive approaches when evaluated automatically and by humans.

Copied to clipboard

Hannah Rashkin, Elizabeth Clark, Fantine Huot, Mirella Lapata

Challenge:	Current models provide specific and mostly accurate writing feedback, but they fail to identify the biggest writing issue in the story and to correctly decide when to offer critical vs. positive feedback.
Approach:	They propose a task that corrupts 1,300 stories to intentionally introduce writing issues to study model performance.
Outcome:	The proposed model performs well in a controlled task with human and automatic evaluation metrics.

Compositional Generalisation for Explainable Hate Speech Detection (2025.emnlp-main)

Copied to clipboard

Agostina Calabrese, Tom Sherborne, Björn Ross, Mirella Lapata

Document Summarization with Latent Queries (2022.tacl-1)

Challenge:	Hate speech detection models struggle to generalise beyond their training data . dataset biases and the use of sentence-level labels fail to teach the underlying structure of hate speech.
Approach:	They propose to use a dataset to train models with fine-grained, span-level annotations . they find that combinations of expressions that deviate from those seen during training are difficult to detect .
Outcome:	The proposed model can generalise to a dataset with equal frequency across all contexts while achieving state-of-the-art performance on the human-sourced PLEAD.

Copied to clipboard

Yumo Xu, Mirella Lapata

Disentangled Sequence to Sequence Learning for Compositional Generalization (2022.acl-long)

Challenge:	Existing benchmarks for query-focused summarization are small for training large neural models.
Approach:	They propose a unified modeling framework for query-focused summarization . they model queries as discrete latent variables over document tokens .
Outcome:	The proposed framework outperforms strong comparison systems across benchmarks, query types, document settings, and target domains.

Copied to clipboard

Text Generation from Discourse Representation Structures (2021.naacl-main)

Challenge:	Existing models struggle to generalize to unseen compositions of seen components . a new approach allows for disentangled representations and better generalization .
Approach:	They propose an extension to sequence-to-sequence models which encourage disentanglement by re-encoding source input.
Outcome:	The proposed extension delivers better generalization and more disentangled representations . human expressions can be understood by combining known atomic components .

Copied to clipboard

Multilingual Summarization with Factual Consistency Evaluation (2023.findings-acl)

Challenge:	Existing models to generate text from formal meaning representations based on Discourse Representation Structures (DRSs) .
Approach:	They propose neural models to generate text from formal meaning representations based on Discourse Representation Structures (DRSs).
Outcome:	The proposed model achieves competitive performance on the GMB benchmark against several strong baselines.

Copied to clipboard

Roee Aharoni, Shashi Narayan, Joshua Maynez, Jonathan Herzig, Elizabeth Clark, Mirella Lapata

Few-Shot Learning for Opinion Summarization (2020.emnlp-main)

Challenge:	Abstractive summarization models generate factually inconsistent summaries, reducing their utility for real-world applications.
Approach:	They propose to use data filtering and controlled generation to detect hallucinations in machine generated summaries.
Outcome:	The proposed models detect factual inconsistencies in machine generated summaries, but they focus on English only.

Copied to clipboard

Arthur Bražinskas, Mirella Lapata, Ivan Titov

Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised (D18-1)

Challenge:	a recent study shows that abstractive summarization models fail to capture their essential properties due to the high cost of summary production.
Approach:	They propose a few-shot framework for abstractive opinion summarization that bootstraps the output of an unsupervised model.
Outcome:	The proposed framework outperforms extractive and abstractive methods on Amazon and Yelp datasets.

Copied to clipboard

Stefanos Angelidis, Mirella Lapata

Sentiment Analysis

Challenge:	Existing methods for opinion summarization are knowledge-lean and require light supervision.
Approach:	They propose a neural framework for opinion summarization from online product reviews which is knowledge-lean and only requires light supervision.
Outcome:	The proposed framework improves over baselines and shows that opinion summaries are preferred by human judges according to multiple criteria.

Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQA (2024.findings-emnlp)

Copied to clipboard

Wenyu Huang, Guancheng Zhou, Hongru Wang, Pavlos Vougiouklis, Mirella Lapata, Jeff Pan

PixT3: Pixel-based Table-To-Text Generation (2024.acl-long)

Challenge:	Recent studies suggest that Knowledge Graphs (KGs) contain valuable external knowledge for LLMs.
Approach:	They propose to model a conditional subgraph retrieval task handled by small language models and use a subgraph identifier as a special token to retrieve subgraphs.
Outcome:	The proposed model achieves competitive retrieval performance compared to state-of-the-art models relying on 7B parameters.

Copied to clipboard

Iñigo Alonso, Eneko Agirre, Mirella Lapata

Structured Data in NLP

Challenge:	Table-to-text generation is a visual recognition task that uses textual descriptions from structured inputs.
Approach:	They propose to rethink data-to-text generation as a visual recognition task by removing the need for rendering the input in a string format.
Outcome:	The proposed model overcomes the challenges of linearization and input size limitations and is applicable to open-ended and controlled generation settings.

Long-Form Information Alignment Evaluation Beyond Atomic Facts (2025.emnlp-main)

Copied to clipboard

Danna Zheng, Mirella Lapata, Jeff Z. Pan

Text Generation from Knowledge Graphs with Graph Transformers (N19-1)

Challenge:	Existing fine-grained methods for information alignment evaluation neglect inter-fact dependencies, enabling subtle vulnerabilities.
Approach:	They propose MontageLie, a benchmark that "montages" truthful statements without introducing explicit hallucinations.
Outcome:	The proposed framework outperforms existing fine-grained methods by over 8% . it is a novel approach for enhancing trust and reducing hallucinations .

Copied to clipboard

Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata, Hannaneh Hajishirzi

Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation (2025.acl-long)

Challenge:	Existing methods for generating text with structured inputs are expensive and require manual annotation.
Approach:	They propose a graph transforming encoder which leverages relational structure of knowledge graphs without imposing linearization or hierarchical constraints.
Outcome:	The proposed system produces more informative texts than competing methods.

Copied to clipboard

Wenyu Huang, Pavlos Vougiouklis, Mirella Lapata, Jeff Z. Pan

Generating Summaries with Topic Templates and Structured Convolutional Decoders (P19-1)

Challenge:	Multi-hop Question Answering (MHQA) adds layers of complexity to question answering tasks.
Approach:	They explore how LMs respond to multi-hop questions by permuting search results under various configurations.
Outcome:	The proposed model outperforms decoder-only models in MHQA tasks despite being significantly smaller in size .

Copied to clipboard

Laura Perez-Beltrachini, Yang Liu, Mirella Lapata

Meta-Learning a Cross-lingual Manifold for Semantic Parsing (2023.tacl-1)

Challenge:	Existing neural generation approaches create multi-sentence text as a single sequence . Existing approaches create multiple sentences as if they were a sequence based on content structure .
Approach:	They propose a structured convolutional decoder that is guided by the content structure of target summaries.
Outcome:	The proposed model outperforms existing decoders on three datasets representing different domains.

Copied to clipboard

Tom Sherborne, Mirella Lapata

Visual Storytelling with Question-Answer Plans (2023.findings-emnlp)

Challenge:	Recent work has found success with machine translation or zero-shot methods . however, these approaches can struggle to model how native speakers ask questions .
Approach:	They propose a meta-learning algorithm to leverage minimal annotated examples in new languages for few-shot cross-lingual semantic parsing.
Outcome:	The proposed approach trains a parser with maximum sample efficiency in six languages on ATIS.

Copied to clipboard

Danyang Liu, Mirella Lapata, Frank Keller

Dolomites: Domain-Specific Long-Form Methodical Tasks (2025.tacl-1)

Challenge:	Existing models focus on enhancing the representation of image sequences, but the stories are repetitive, illogical, and lacking in detail.
Approach:	They propose a framework which integrates visual representations with pretrained language models and planning.
Outcome:	The proposed framework combines visual representations with pretrained language models and planning.

Copied to clipboard

Chaitanya Malaviya, Priyanka Agrawal, Kuzman Ganchev, Pranesh Srinivasan, Fantine Huot, Jonathan Berant, Mark Yatskar, Dipanjan Das, Mirella Lapata, Chris Alberti

Challenge:	Experts in various fields perform methodical writing tasks to plan, organize, and report their work.
Approach:	They propose a benchmark with specifications for 519 methodical writing tasks . they use expert revisions of up to 10 model-generated examples to evaluate contemporary language models.
Outcome:	The proposed benchmark includes specifications for 519 methodical writing tasks . it includes examples with input and output examples, and is available at https://dolomites-benchmark.github.io/ .

Sentence Compression for Arbitrary Languages via Multilingual Pivoting (D18-1)

Copied to clipboard

Jonathan Mallinson, Rico Sennrich, Mirella Lapata

Document Modeling with External Attention for Sentence Extraction (P18-1)

Challenge:	a new study advocates the use of bilingual corpora for sentence compression models . previous work focused on word deletion, while others view sentence compression as a general text rewriting problem.
Approach:	They propose to use bilingual corpora for training sentence compression models.
Outcome:	The proposed model can be trained for any language as long as a bilingual corpus is available . it performs arbitrary rewrites without access to compression specific data .

Copied to clipboard

Shashi Narayan, Ronald Cardenas, Nikos Papasarantopoulos, Shay B. Cohen, Mirella Lapata, Jiangsheng Yu, Yi Chang

Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning (2023.findings-acl)

Challenge:	Document modeling is essential to a variety of natural language understanding tasks.
Approach:	They propose to use external information to improve document modeling for sentence extraction problems.
Outcome:	The proposed model outperforms baseline models on document summarization and answer selection tasks and achieves state-of-the-art results on WikiQA and NewsQA.

Copied to clipboard

Archer: A Human-Labeled Text-to-SQL Dataset with Arithmetic, Commonsense and Hypothetical Reasoning (2024.eacl-long)

Challenge:	Existing approaches to compositional generalization have been designed with semantic parsing in mind.
Approach:	They propose a disentangled sequence-to-sequence model which encourages more disentanglement and improves its compute and memory efficiency.
Outcome:	The proposed model improves generalization performance across existing tasks and datasets and a new machine translation benchmark.

Copied to clipboard

Danna Zheng, Mirella Lapata, Jeff Pan

Programming Languages in NLP

Challenge:	Existing text-to-SQL datasets that capture complex reasoning are limited by their execution accuracy.
Approach:	They present a bilingual text-to-SQL dataset specific to complex reasoning . their evaluation shows that Archer challenges the capabilities of current models .
Outcome:	The proposed dataset challenges state-of-the-art models with 6.73% execution accuracy . the dataset contains 1,042 English and 1,042, Chinese questions and 521 unique SQL queries .

Multi-Step Inference for Reasoning Over Paragraphs (2020.emnlp-main)

Copied to clipboard

Jiangming Liu, Matt Gardner, Shay B. Cohen, Mirella Lapata

Reasoning

Challenge:	Existing models for complex reasoning use symbols or black-box transformers . a compositional model can chain together free-form predicates and logical connectives .
Approach:	They propose a compositional model that finds relevant sentences and then chains them together using neural modules.
Outcome:	The proposed model improves performance on a recently-introduced dataset.

Alignment-free Cross-lingual Semantic Role Labeling (2020.emnlp-main)

Copied to clipboard

Rui Cai, Mirella Lapata

Compositional Generalization for Data-to-Text Generation (2023.findings-emnlp)

Challenge:	Existing approaches to semantic role labeling rely on word alignments, translation engines or preprocessing tools.
Approach:	They propose a cross-lingual semantic role labeling model which only requires annotations in a source language and access to raw text in .
Outcome:	The proposed model minimizes the effort required to construct annotations or models for a new target language.

Copied to clipboard

Xinnuo Xu, Ivan Titov, Mirella Lapata

Experience Grounds Language (2020.emnlp-main)

Challenge:	Data-to-text generation models can be used to generate textual descriptions from structured data . despite advances, systems struggle when confronted with unseen combinations of predicates .
Approach:	They propose a data-to-text generation model that addresses compositional generalization by clustering predicates into groups.
Outcome:	The proposed model outperforms T5-baselines in all evaluation metrics.

Copied to clipboard

Yonatan Bisk, Ari Holtzman, Jesse Thomason, Jacob Andreas, Yoshua Bengio, Joyce Chai, Mirella Lapata, Angeliki Lazaridou, Jonathan May, Aleksandr Nisnevich, Nicolas Pinto, Joseph Turian

Generating Visual Stories with Grounded and Coreferent Characters (2026.tacl-1)

Challenge:	aaron carroll: language understanding research is held back by a failure to relate language to the physical world it describes and to social interactions it facilitates. carroll says successful linguistic communication relies on a shared experience of the world.
Approach:	They propose to use a broader physical and social context to address communication problems . they argue that the current success of representation learning approaches is limited .
Outcome:	a new study suggests that the current success of representation learning requires a parallel tradition of research on the broader physical and social context of language to address the deeper questions of communication.

Copied to clipboard

Danyang Liu, Mirella Lapata, Frank Keller

Visual Data in NLP

Challenge:	Experimental results show that our model generates visual stories with consistent and coreferent character mentions compared to baselines and state-of-the-art systems.
Approach:	They propose a character-centric approach to visual story generation that uses visual and textual character coreference chains to enrich the VIST benchmark.
Outcome:	The proposed model generates visual stories with consistent and coreferent character mentions compared to baselines and state-of-the-art systems.

Learning to Plan and Generate Text with Citations (2024.acl-long)

Copied to clipboard

Constanza Fierro, Reinald Kim Amplayo, Fantine Huot, Nicola De Cao, Joshua Maynez, Shashi Narayan, Mirella Lapata

Informative and Controllable Opinion Summarization (2021.eacl-main)

Challenge:	Large language models (LLMs) are increasingly useful in information-seeking scenarios, ranging from answering simple questions to generating responses to search-like queries.
Approach:	They propose to use plan-based models to improve faithfulness, grounding, and controllability of generated content and its organization.
Outcome:	The proposed models improve faithfulness, grounding, and controllability of generated content and its organization.

Copied to clipboard

Reinald Kim Amplayo, Mirella Lapata

Unsupervised Opinion Summarization as Copycat-Review Generation (2020.acl-main)

Challenge:	Existing methods for opinion summarization use a two-stage extractive and abstractive approach to generate summaries for reviews of a specific target.
Approach:	They propose a framework for opinion summarization that condenses all input reviews into multiple dense vectors which serve as input to an abstractive model.
Outcome:	The proposed framework produces more informative summaries and allows to take user preferences into account using a zero-shot customization technique.

Copied to clipboard

Arthur Bražinskas, Mirella Lapata, Ivan Titov

Dscorer: A Fast Evaluation Metric for Discourse Representation Structure Parsing (2020.acl-main)

Challenge:	Recent work on opinion summarization has focused on extracting fragments from reviews, but we use novel sentences to generate abstractive summaries.
Approach:	They propose an abstractive summarizer which does not use summaries in training and is trained end-to-end on a large collection of reviews.
Outcome:	The proposed model produces fluent and coherent summaries reflecting consensus opinions on Amazon and Yelp reviews.

Copied to clipboard

Bootstrapping Generators from Noisy Data (N18-1)

Challenge:	Discourse representation structures (DRSs) are scoped semantic representations for texts of arbitrary length.
Approach:	They propose a new metric which converts box-style DRSs to graphs and measures the overlap of n-grams.
Outcome:	Experiments show that Dscorer computes accuracy scores that are correlated with Counter at a fraction of the time.

Copied to clipboard

Laura Perez-Beltrachini, Mirella Lapata

Zero-Shot Crosslingual Sentence Simplification (2020.emnlp-main)

Challenge:	Existing methods for data-to-text generation focus on learning correspondences between structured data and associated texts.
Approach:	They aim to bootstrap generators from large scale datasets where data and related texts are loosely aligned.
Outcome:	The proposed model improves on a vanilla encoder-decoder which relies on soft attention.

Copied to clipboard

Jonathan Mallinson, Rico Sennrich, Mirella Lapata

Text Summarization with Pretrained Encoders (D19-1)

Challenge:	Recent approaches to simplification have shown promising results with encoder-decoder models trained on large amounts of parallel data which often only exists in English.
Approach:	They propose a model which transfers simplification knowledge from English to another language while generalizing across languages and tasks.
Outcome:	Empirical results show that the proposed model performs better than unsupervised and pivot-based methods.

Copied to clipboard

Yang Liu, Mirella Lapata

Noisy Self-Knowledge Distillation for Text Summarization (2021.naacl-main)

Challenge:	Existing pretraining languages such as ELMo and GPT have advanced a wide range of tasks.
Approach:	They propose a novel document-level encoder based on BERT which can express the semantics of a document and obtain representations for its sentences.
Outcome:	The proposed model achieves state-of-the-art in extractive and abstractive settings.

Copied to clipboard

Yang Liu, Sheng Shen, Mirella Lapata

Data-to-text Generation with Entity Modeling (P19-1)

Challenge:	Existing approaches to summarize text using a single reference and noisy datasets are ill-suited to summarising on single reference datasets.
Approach:	They propose to use self-knowledge distillation to improve text summarization by generating smoothed labels for students and teachers to reduce model uncertainty.
Outcome:	The proposed framework improves on pretrained and non-pretrained models on three benchmarks.

Copied to clipboard

Ratish Puduppully, Li Dong, Mirella Lapata

Neural Latent Extractive Document Summarization (D18-1)

Challenge:	Recent approaches to data-to-text generation have shown great promise thanks to the use of large-scale datasets and the application of neural network architectures which are trained end-to end.
Approach:	They propose an entity-centric neural architecture for data-to-text generation which uses hierarchical attention to create entity-specific representations which are dynamically updated.
Outcome:	The proposed model outperforms baselines in automatic and human evaluation on the RotoWire benchmark and a five-times larger dataset on the baseball domain.

Copied to clipboard

Xingxing Zhang, Mirella Lapata, Furu Wei, Ming Zhou

Models and Datasets for Cross-Lingual Summarisation (2021.emnlp-main)

Challenge:	Existing summarization paradigms focus on extractive summarizing based on sentence level labels .
Approach:	They propose a latent variable extractive model where sentences are viewed as latent variables and sentences with activated variables are used to infer gold summaries.
Outcome:	The proposed model outperforms a strong extractive baseline trained on rule-based labels and performs competitively with several recent models.

Copied to clipboard

Laura Perez-Beltrachini, Mirella Lapata

Sentence Centrality Revisited for Unsupervised Summarization (P19-1)

Challenge:	Recent years have witnessed increased interest in abstractive summarisation thanks to the popularity of neural network models and the availability of datasets containing hundreds of thousands of document-summary pairs.
Approach:	They propose to create a cross-lingual summarisation corpus with long documents in a source language associated with multi-sentence summaries in . target language.
Outcome:	The proposed task can be applied to several other languages and covers twelve languages and directions.

Copied to clipboard

Coarse-to-Fine Decoding for Neural Semantic Parsing (P18-1)

Challenge:	Experimental results on three news summarization datasets representative of different languages and writing styles show that our approach outperforms strong baselines by a wide margin.
Approach:	They propose an unsupervised approach that uses a popular ranking algorithm to compute node centrality.
Outcome:	The proposed approach outperforms baselines on three news summarization datasets representative of different languages and writing styles.

Copied to clipboard

Li Dong, Mirella Lapata

Little Red Riding Hood Goes around the Globe: Crosslingual Story Planning and Generation with Large Language Models (2024.lrec-main)

Challenge:	Experimental results show that semantic parsing is more efficient than using simple decoders.
Approach:	They propose a structure-aware neural architecture which decomposes the semantic parsing process into two stages.
Outcome:	The proposed architecture consistently improves performance on four datasets characteristic of different domains and meaning representations.

Copied to clipboard

Evgeniia Razumovskaia, Joshua Maynez, Annie Louis, Mirella Lapata, Shashi Narayan

Aspect-Controllable Opinion Summarization (2021.emnlp-main)

Challenge:	Existing work has demonstrated the effectiveness of planning for story generation exclusively in a monolingual setting focusing primarily on English.
Approach:	They propose a task of crosslingual story generation with planning to leverage the creative and reasoning capabilities of large pretrained language models to generate stories in multiple languages.
Outcome:	The proposed task combines planning and planning in a monolingual setting and demonstrates that plans which structure stories into three acts lead to more coherent and interesting narratives while allowing to explicitly control their content and structure.

Copied to clipboard

Reinald Kim Amplayo, Stefanos Angelidis, Mirella Lapata

Context-Aware Hierarchical Merging for Long Document Summarization (2025.findings-acl)

Challenge:	Recent work on opinion summarization produces general summaries based on reviews and popularity of opinions expressed in them.
Approach:	They propose an approach that generates customized opinion summaries based on aspect queries.
Outcome:	The proposed model outperforms the current state of the art and generates personalized summaries by controlling the number of aspects discussed in them.

Copied to clipboard

Litu Ou, Mirella Lapata

Discourse Representation Parsing for Sentences and Documents (P19-1)

Challenge:	Hierarchical merging is a technique used to summarize very long texts . it can amplify LLM hallucinations, increasing the risk of factual inaccuracies .
Approach:	They propose to enrich hierarchical merging with context from the source document to reduce the risk of factual inaccuracies.
Outcome:	The proposed methods outperform zero-shot and hierarchical merging baselines on legal and narrative datasets.

Copied to clipboard

Movie Plot Analysis via Turning Point Identification (D19-1)

Challenge:	Experimental results show that our model outperforms competitive baselines by a wide margin.
Approach:	They propose a neural model which parses discourse structures of arbitrary length and granularity.
Outcome:	The proposed model outperforms baseline models on sentence- and document-level benchmarks.

Copied to clipboard

Pinelopi Papalampidi, Frank Keller, Mirella Lapata

Challenge:	Using computational literary analysis, we analyze novels, plays, and screenplays for their turning points.
Approach:	They propose to use turning points to analyze screenplays and plot synopses as tools for analysis . they propose to build a neural network model that identifies turning points in plot synoopse .
Outcome:	The proposed model outperforms baselines based on state-of-the-art sentence representations and expected position of turning points.

𝜇PLAN: Summarizing using a Content Plan as Cross-Lingual Bridge (2024.eacl-long)

Copied to clipboard

Fantine Huot, Joshua Maynez, Chris Alberti, Reinald Kim Amplayo, Priyanka Agrawal, Constanza Fierro, Shashi Narayan, Mirella Lapata

Extractive Opinion Summarization in Quantized Transformer Spaces (2021.tacl-1)

Challenge:	Recent advances in abstractive summarization have focused on English, but more recently, with the advent of large pre-trained models, the task is becoming more complex.
Approach:	They propose an approach to cross-lingual summarization that uses an intermediate planning step as a cross-linguistic bridge.
Outcome:	The proposed approach achieves state-of-the-art in terms of informativeness and faithfulness on the XWikis dataset.

Copied to clipboard

Stefanos Angelidis, Reinald Kim Amplayo, Yoshihiko Suhara, Xiaolan Wang, Mirella Lapata

Semi-Supervised Semantic Role Labeling with Cross-View Training (D19-1)

Challenge:	Existing work on opinion summarization focuses on aggregating opinions among reviews . et al., 2018; see etal., 2019; liu eto, 2019) demonstrate the potential of opinion summaries.
Approach:	They propose an unsupervised system for extractive opinion summarization based on vector-quantized variables and an extraction algorithm.
Outcome:	The proposed method is validated by human studies showing that judges prefer it over baselines.

Copied to clipboard

Rui Cai, Mirella Lapata

Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing (2023.tacl-1)

Challenge:	Recent approaches rely on expensive annotations and are unavailable in low resource scenarios (e.g., rare languages or domains).
Approach:	They propose an end-to-end SRL model which leverages unlabeled data and propose to reduce the annotation effort involved via semi-supervised learning.
Outcome:	The proposed model outperforms the state-of-the-art in English and consistently improves performance in other languages, including Chinese, German, and Spanish.

Copied to clipboard

Tom Sherborne, Tom Hosking, Mirella Lapata

Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing (2025.findings-acl)

Challenge:	Existing work on cross-lingual semantic parsing has focused on English . a few-shot approach to parse from natural languages is comparatively unexplored .
Approach:	They propose a method that minimizes cross-lingual divergence between probabilistic latent variables by Optimal Transport.
Outcome:	The proposed method improves performance even without parallel input translations on two datasets.

Copied to clipboard

Irina Saparina, Mirella Lapata

Programming Languages in NLP

Challenge:	Natural language interfaces are often ambiguous, vague, or underspecified, giving rise to multiple valid interpretations.
Approach:	They propose a modular approach that resolves ambiguity using natural language interpretations before mapping them to logical forms.
Outcome:	The proposed approach improves interpretation coverage and generalizes across datasets with different annotation styles, database structures, and ambiguity types.

Zero-Shot Cross-lingual Semantic Parsing (2022.acl-long)

Copied to clipboard

Tom Sherborne, Mirella Lapata

Debating for Better Reasoning in Vision-Language Models (2025.findings-emnlp)

Challenge:	Recent work in cross-lingual semantic parsing assumes access to high-quality machine translation systems and word alignment tools.
Approach:	They propose a multi-task encoder-decoder model to transfer parsing knowledge to additional languages using only English-logical form paired data and in-domain natural language corpora.
Outcome:	The proposed model performs significantly above translation-based baselines and competes with the supervised upper-bound.

Copied to clipboard

Ashutosh Adhikari, Mirella Lapata

Confidence Modeling for Neural Semantic Parsing (P18-1)

Challenge:	Large Language Models (LLMs) gain expertise across diverse domains and modalities, a new study shows . scalable oversight becomes challenging when their capabilities surpass human evaluators.
Approach:	a new study extends the debate paradigm to a multimodal setting . it explores the potential for blind models to supervise and enhance the performance of sighted ones.
Outcome:	The proposed framework outperforms individual LLMs on multimodal tasks . it allows blind models to supervise and enhance the performance of sighted models .

Copied to clipboard

Li Dong, Chris Quirk, Mirella Lapata

Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books (2026.findings-acl)

Challenge:	Experimental results show that neural semantic parsers are difficult to interpret due to their complexity.
Approach:	They propose to use confidence models to estimate predictions for neural semantic parsers . they outline three major causes of uncertainty and use metrics to quantify them .
Outcome:	The proposed model outperforms a widely used method that relies on posterior probability and improves interpretation quality.

Copied to clipboard

Argyrios Papoudakis, Mirella Lapata, Frank Keller

Reasoning

Challenge:	Character description generation is an important capability for narrative-focused applications . however, generating accurate character descriptions from long-form narratives is challenging . enabling built-in reasoning mode of current LLMs often degrades performance .
Approach:	They propose a framework that decouples reasoning from generation by generating a structured QA reasoning trace and a generation model that conditions on this trace to produce the final character description.
Outcome:	The proposed framework improves faithfulness, informativeness, and grounding over long-context baselines.

Meta-Learning for Domain Generalization in Semantic Parsing (2021.naacl-main)

Copied to clipboard

Bailin Wang, Mirella Lapata, Ivan Titov

Conditional Generation with a Question-Answering Blueprint (2023.tacl-1)

Challenge:	Existing approaches to parsing use standard supervised learning, but little attention has been given to domain generalization.
Approach:	They propose a meta-learning framework which targets zero-shot domain generalization for semantic parsing.
Outcome:	The proposed framework significantly boosts parser performance on English and Chinese spider datasets.

Copied to clipboard

Shashi Narayan, Joshua Maynez, Reinald Kim Amplayo, Kuzman Ganchev, Annie Louis, Fantine Huot, Anders Sandholm, Dipanjan Das, Mirella Lapata

Question Answering

Challenge:	Neural generation models often struggle to identify which content units are salient.
Approach:	They propose a new conceptualization of text plans as a sequence of question-answer pairs . they propose QA blueprints as QA proxy for content selection and planning .
Outcome:	The proposed model improves existing datasets with QA blueprints as proxy for content selection and planning.

Structured Alignment Networks for Matching Sentences (D18-1)

Copied to clipboard

Yang Liu, Matt Gardner, Mirella Lapata

Textual Inference

Challenge:	Many tasks in natural language processing involve comparing two sentences to compute some notion of relevance, entailment, or similarity.
Approach:	They propose a model of structured alignments between sentences to compare two sentences by matching their latent structures.
Outcome:	The proposed model is differentiable and trained only on the matching objective.

Semantic Parsing for Conversational Question Answering over Knowledge Graphs (2023.eacl-main)

Copied to clipboard

Laura Perez-Beltrachini, Parag Jain, Emilio Monti, Mirella Lapata

Natural Language Interfaces

Challenge:	Recent years have seen an increasing number of applications aiming to build conversational interfaces based on information retrieval and user recommendation.
Approach:	They develop a dataset where user questions are annotated with Sparql parses and system answers correspond to execution results thereof.
Outcome:	The proposed parsers can be used to ground questions into queries over definitions in a knowledge graph with large vocabularies.

Single Document Summarization as Tree Induction (N19-1)

Copied to clipboard

Yang Liu, Ivan Titov, Mirella Lapata

CHIRON: Rich Character Representations in Long-Form Narratives (2024.findings-emnlp)

Challenge:	Existing approaches to extractive summarization use recurrent neural networks to model document . Existing systems use a vector representation for each sentence to generate a summary .
Approach:	They propose a model that induces a multi-root dependency tree while predicting the output summary.
Outcome:	The proposed model performs competitively against state-of-the-art methods on two benchmark datasets.

Copied to clipboard

Alexander Gurung, Mirella Lapata

Representation Learning

Challenge:	Existing systems for character representation have simplified the problem of representing complex characters via graphs and brief character descriptions.
Approach:	They propose a ‘character sheet’ based representation that organizes and filters textual information about characters.
Outcome:	The proposed representation organizes and filters textual information about characters and is better and more flexible than previous models.

University of Edinburgh’s submission to the Document-level Generation and Translation Shared Task (D19-56)

Copied to clipboard

Ratish Puduppully, Jonathan Mallinson, Mirella Lapata

Decomposed Opinion Summarization with Verified Aspect-Aware Modules (2025.findings-acl)

Challenge:	University of Edinburgh participated in all six tracks: NLG, MT, and MT+NLG with English and German as targeted languages.
Approach:	The University of Edinburgh participated in all six tracks: NLG, MT, and MT+NLG . they submitted a multilingual system based on the Content Selection and Planning model .
Outcome:	The University of Edinburgh participated in all six tracks with English and German as target languages.

Copied to clipboard

Miao Li, Jey Han Lau, Eduard Hovy, Mirella Lapata

Evaluating LLMs for Targeted Concept Simplification for Domain-Specific Texts (2024.emnlp-main)

Challenge:	Existing methods for summarizing opinions from large-scale online reviews are not available for crowdsourcing and are difficult to crowdsource.
Approach:	They propose a domain-agnostic modular approach guided by review aspects to separate tasks of aspect identification, opinion consolidation, and meta-review synthesis to enable greater transparency and ease of inspection.
Outcome:	The proposed approach generates more grounded summaries than baseline models, as verified through automated and human evaluations.

Copied to clipboard

Sumit Asthana, Hannah Rashkin, Elizabeth Clark, Fantine Huot, Mirella Lapata

Paraphrasing

Challenge:	Simplifying the entire text makes it understandable but sometimes removes important details.
Approach:	They propose a simplification task for rewriting text to help readers comprehend text containing unfamiliar concepts and introduce a dataset of 22k definitions from 13 academic domains paired with a difficult concept within each definition.
Outcome:	The proposed model outperforms open-source and commercial models on the task and human judges prefer explanations over simplifications of the difficult concept.

Bootstrapping a Crosslingual Semantic Parser (2020.findings-emnlp)

Copied to clipboard

Tom Sherborne, Yumo Xu, Mirella Lapata

Low-Rank Adaptation for Multilingual Summarization: An Empirical Study (2024.findings-naacl)

Challenge:	Recent advances in semantic parsing are limited to English but professional translation can be prohibitively expensive.
Approach:	They adapt a semantic parser trained on a single language to new languages and multiple domains with minimal annotation.
Outcome:	The proposed approach achieves parsing accuracy within 2% of translation using only 50% of training data.

Copied to clipboard

Chenxi Whitehouse, Fantine Huot, Jasmijn Bastings, Mostafa Dehghani, Chu-Cheng Lin, Mirella Lapata

Explainable Abuse Detection as Intent Classification and Slot Filling (2022.tacl-1)

Challenge:	Pre-trained Large Language Models have significantly advanced NLP, but their ever-increasing size poses significant challenges for conventional fine-tuning.
Approach:	They investigate the potential of Low-Rank Adaptation (LoRA) in multilingual summarization, a task that is challenging and relatively unexplored.
Outcome:	The proposed method outperforms full fine-tuning and cross-lingual transfer strategies in multilingual summarization tasks.

Copied to clipboard

Agostina Calabrese, Björn Ross, Mirella Lapata

Information Retrieval

Challenge:	Existing models learn what abuse is from labeled examples and base their predictions on spurious cues.
Approach:	They propose a machine-friendly representation of the policy that moderators wish to enforce by breaking it down into intents and slots.
Outcome:	The proposed model breaks down a social media policy into intents and slots and provides a rationale for its decisions.

Learning from Executions for Semantic Parsing (2021.naacl-main)

Copied to clipboard

Bailin Wang, Mirella Lapata, Ivan Titov

Conversational Semantic Parsing using Dynamic Context Graphs (2023.emnlp-main)

Challenge:	Semantic parsing aims at translating natural language (NL) utterances onto machine-interpretable programs.
Approach:	They propose to encourage a parser to generate executable programs for unlabeled NL utterances.
Outcome:	The proposed training objectives outperform conventional methods on Overnight and GeoQuery.

Copied to clipboard

Parag Jain, Mirella Lapata

Natural Language Interfaces

Challenge:	Existing work on conversational semantic parsing has focused on answering questions in isolation . whereas existing work on KBQA is focused on resolving questions in the context of natural language questions .
Approach:	They propose to model conversational semantic parsing over general purpose knowledge graphs with millions of entities and thousands of relation-types by exploiting its underlying structure and encoding it with a graph neural network.
Outcome:	The proposed model is better at processing discourse information and longer interactions . it is better than static models at handling ellipsis and coreference, the authors show .

What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations (2025.acl-long)

Copied to clipboard

Dongqi Liu, Chenxi Whitehouse, Xi Yu, Louis Mahon, Rohit Saxena, Zheng Zhao, Yifu Qiu, Mirella Lapata, Vera Demberg

Partners in Crime: Multi-view Sequential Inference for Movie Understanding (D19-1)

Challenge:	VISTA dataset contains 18,599 recorded AI conference presentations . large multimodal models exhibit reduced performance in scientific contexts, study shows .
Approach:	They propose a dataset specifically designed for video-to-text summarization in scientific domains.
Outcome:	This paper compares the performance of large models with human models and shows that they improve on human models.

Copied to clipboard

Nikos Papasarantopoulos, Lea Frermann, Mirella Lapata, Shay B. Cohen

Challenge:	Existing multi-view learning approaches are tested in unsupervised setups, allowing for learning of representation for monolithic data points, not sequences.
Approach:	They propose a neural architecture paired with a novel objective for incremental inference that integrates multi-view information for sequence prediction problems.
Outcome:	The proposed model outperforms previous work and strong baselines on two crime cases and speaker type tagging tasks that contribute to movie understanding.

Hierarchical Transformers for Multi-Document Summarization (P19-1)

Copied to clipboard

Yang Liu, Mirella Lapata

Hierarchical Sketch Induction for Paraphrase Generation (2022.acl-long)

Challenge:	Existing models for multidocument summarization have been developed that can process multiple documents in a hierarchical manner.
Approach:	They propose a neural summarization model which can process multiple input documents and distill Transformer architecture with the ability to encode documents in a hierarchical manner.
Outcome:	The proposed model improves on the WikiSum dataset and can process multiple documents in a hierarchical manner.

Copied to clipboard

Tom Hosking, Hao Tang, Mirella Lapata

A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation (2022.acl-long)

Challenge:	Existing models of paraphrase generation are based on a syntactic sketch, but prior work has included inductive bias.
Approach:	They propose a method for learning decompositions of dense encodings as a sequence of discrete latent variables that make iterative refinements of increasing granularity.
Outcome:	The proposed model improves on human paraphrase generation by predicting syntactic sketches at test time.

Copied to clipboard

Shashi Narayan, Gonçalo Simões, Yao Zhao, Joshua Maynez, Dipanjan Das, Michael Collins, Mirella Lapata

Memory-Based Semantic Parsing (2021.tacl-1)

Challenge:	Composition Sampling is a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies.
Approach:	They propose a method to generate diverse outputs for conditional generation . they use a plan-based neural generation model that is trained to create a composition of the output and then generate by conditioning on it and the input.
Outcome:	The proposed method avoids text degeneration by first sampling a composition in the form of an entity chain and then using beam search to generate the best possible text grounded to this entity chain.

Copied to clipboard

Parag Jain, Mirella Lapata

A Modular Approach for Multimodal Summarization of TV Shows (2024.acl-long)

Challenge:	Existing models for context-dependent semantic parsing focus on parse utterances in isolation . a decoder cannot copy or modify the parser from the previous utterrance .
Approach:	They propose to represent contextual information using an external memory by maintaining the cumulative meaning of sequential user utterances.
Outcome:	The proposed model can better process context-dependent information without task-specific decoders.

Copied to clipboard

Louis Mahon, Mirella Lapata

BookWorm: A Dataset for Character Description and Analysis (2024.findings-emnlp)

Challenge:	In this paper, we address the task of summarizing television shows, which touches key areas in AI research.
Approach:	They propose a modular approach where separate components perform specialized sub-tasks . they propose atomic facts to measure precision and recall of generated summaries .
Outcome:	The proposed method produces higher quality summaries than comparison models on a recently released dataset.

Copied to clipboard

Argyrios Papoudakis, Mirella Lapata, Frank Keller

Information Retrieval

Challenge:	Characters are at the heart of every story, driving the plot and engaging readers.
Approach:	They propose to use a book-length character description dataset to evaluate character-based models.
Outcome:	The proposed model outperforms hierarchical models in both tasks and is based on a novel novel character description dataset.

Explainability and Hate Speech: Structured Explanations Make Social Media Moderators Faster (2024.acl-short)

Copied to clipboard

Agostina Calabrese, Leonardo Neves, Neil Shah, Maarten Bos, Björn Ross, Mirella Lapata, Francesco Barbieri

Unsupervised Opinion Summarization with Noising and Denoising (2020.acl-main)

Challenge:	Existing studies have shown that explanations can support content moderators to make faster decisions, but the benefits of such models have not been studied.
Approach:	They propose to use structured explanations to support content moderators to make faster decisions by 7.4%.
Outcome:	The proposed models lower the speed of real-world moderators by 7.4% compared to generic explanations and are often ignored . previous studies have shown that explanations can support moderator's decision making by detecting violations of policies but the benefits have not been studied .

Copied to clipboard

Reinald Kim Amplayo, Mirella Lapata

Factorising Meaning and Form for Intent-Preserving Paraphrasing (2021.acl-long)

Challenge:	Existing methods for abstractive summarization are limited and cannot be easily sourced.
Approach:	They propose a supervised learning model which learns to denoise the input and generate original reviews.
Outcome:	The proposed model improves on the baselines of abstractive and extractive models on a large dataset with only a few reviews and no ground truth summaries.

Copied to clipboard

Tom Hosking, Mirella Lapata

Screenplay Summarization Using Latent Narrative Structure (2020.acl-main)

Challenge:	Existing methods for paraphrasing questions retain original intent but use a different surface form.
Approach:	They propose a method for generating paraphrases of English questions that retain original intent but use a different surface form.
Outcome:	The proposed method generates paraphrases with better tradeoff between semantic preservation and novelty compared to previous methods.

Copied to clipboard

Pinelopi Papalampidi, Frank Keller, Lea Frermann, Mirella Lapata

Multi-view Story Characterization from Movie Plot Synopses and Reviews (2020.emnlp-main)

Challenge:	Experimental results show that latent turning points improve summarization performance over general extractive summarizing models.
Approach:	They propose to explicitly incorporate the underlying structure of narratives into extractive summarization models by treating it as latent.
Outcome:	The proposed model improves on the CSI corpus of screenplays on a CSI episode . it shows that latent turning points correlate with important aspects of the document .

Copied to clipboard

Sudipta Kar, Gustavo Aguilar, Mirella Lapata, Thamar Solorio

Challenge:	Existing methods for characterizing stories by generating tags from synopses suffer from coverage issues.
Approach:	They propose to use synopses and reviews to characterize stories by inferring attributes such as theme and style from written synopsis and reviews.
Outcome:	The proposed model improves over methods that only use synopses and reviews . it can extract a complementary set of story attributes from reviews without supervision .

Compositional Generalization via Semantic Tagging (2021.findings-emnlp)

Copied to clipboard

Attributable and Scalable Opinion Summarization (2023.acl-long)

Challenge:	Existing neural sequence-to-sequence models fail at compositional generalization, i.e., they cannot generalize to unseen compositions of seen components.
Approach:	They propose a decoding framework that preserves expressivity and generality of sequence-to-sequence models while featuring lexicon-style alignments and disentangled information processing.
Outcome:	The proposed framework improves compositional generalization across model architectures, domains, and semantic formalisms on three semantic parsing datasets.

Copied to clipboard

Tom Hosking, Hao Tang, Mirella Lapata

Learning Opinion Summarizers by Selecting Informative Reviews (2021.emnlp-main)

Challenge:	Existing methods for opinion summarization encode sentences from customer reviews into a hierarchical discrete latent space.
Approach:	They propose a method that encodes customer reviews into a hierarchical discrete latent space and then identifies common opinions based on their frequency.
Outcome:	The proposed method generates summaries that are more informative than previous work and more grounded in the input reviews.

Copied to clipboard

Arthur Bražinskas, Mirella Lapata, Ivan Titov

Discourse Representation Structure Parsing (P18-1)

Challenge:	supervised summarization has been traditionally approached with unsupervised, weakly-supervised and few-shot learning techniques.
Approach:	They propose to combine a large dataset of opinion summaries with user reviews to form a supervised summarizer.
Outcome:	The proposed method improves the quality of summarization and reduces hallucinations in the summarizer.

Copied to clipboard

Coarse-to-Fine Query Focused Multi-Document Summarization (2020.emnlp-main)

Challenge:	Existing semantic parsers are data-driven using annotated examples consisting of utterances and their meaning representations.
Approach:	They propose a method which transforms Discourse Representation Structures (DRSs) to trees and develop a structure-aware model which decomposes the decoding process into three stages.
Outcome:	The proposed model outperforms baseline models on the Groningen Meaning Bank (GMB) by a wide margin.

Copied to clipboard

Yumo Xu, Mirella Lapata

Data-to-text Generation with Variational Sequential Planning (2022.tacl-1)

Challenge:	Existing work on query focused multi-document summarization relies heavily on retrieval-style methods.
Approach:	They propose a query-cluster-based model which uses more accurate modules for estimating whether text segments are relevant, likely to contain an answer, and central.
Outcome:	The proposed framework outperforms strong comparison systems on benchmark datasets across domains and query types.

Copied to clipboard

Ratish Puduppully, Yao Fu, Mirella Lapata

Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs (D19-1)

Challenge:	Recent advances in data-to-text generation have greatly facilitated the task of generating textual output from non-linguistic input.
Approach:	They propose a neural model enhanced with a planning component responsible for organizing high-level information in a coherent and meaningful way.
Outcome:	The proposed model outperforms baseline models and is sample-efficient in the face of limited training data.

Copied to clipboard

Bailin Wang, Ivan Titov, Mirella Lapata

Ranking Sentences for Extractive Summarization with Reinforcement Learning (N18-1)

Challenge:	Semantic parsing aims to map natural language utterances onto machine interpretable meaning representations.
Approach:	They propose to instill an inductive bias in the parser to help it distinguish between spurious and correct programs.
Outcome:	The proposed model is highly tractable on WikiTableQuestions and WikiSQL datasets.

Copied to clipboard

Shashi Narayan, Shay B. Cohen, Mirella Lapata

Hierarchical3D Adapters for Long Video-to-text Summarization (2023.findings-eacl)

Challenge:	Abstractive summarization involves various text rewriting operations and has been identified as a sequence-to-sequence problem.
Approach:	They propose a novel algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective.
Outcome:	The proposed algorithm outperforms state-of-the-art extractive and abstractive systems when evaluated automatically and by humans.

Copied to clipboard

Pinelopi Papalampidi, Mirella Lapata

Text-Blueprint: An Interactive Platform for Plan-based Conditional Generation (2023.eacl-demo)

Challenge:	a recent study shows that multimodal summarization is not efficient for long inputs and outputs.
Approach:	They extend a TV episode transcript summarization dataset and create a multimodal variant by collecting full-length videos.
Outcome:	The proposed model can be tuned to perform multimodal summarization tasks efficiently using adapter modules augmented with a hierarchical structure while tuning only 3.8% of model parameters.

Copied to clipboard

Fantine Huot, Joshua Maynez, Shashi Narayan, Reinald Kim Amplayo, Kuzman Ganchev, Annie Priyadarshini Louis, Anders Sandholm, Dipanjan Das, Mirella Lapata

Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (2026.acl-long)

Challenge:	Recent work shows that conditional generation models can be useful to control the text generation process, leading to irrelevant, repetitive, and hallucinated content.
Approach:	They propose a web browser-based demonstration for query-focused summarization that uses a sequence of question-answer pairs as a blueprint plan for guiding text generation.
Outcome:	The proposed model can be used to generate query-focused summarization text using question-answer pairs as a blueprint plan.

Copied to clipboard

Miao Li, Irina Saparina, Alexander Gurung, Mirella Lapata

Reasoning

Challenge:	Recent large language models support inputs of up to 10 million tokens, yet they perform poorly on long-context tasks.
Approach:	They propose a training framework that transfers reasoning capabilities from proxy contexts to full long contexts.
Outcome:	The proposed framework outperforms baseline models with reduced computational overhead.

Data-to-text Generation with Macro Planning (2021.tacl-1)

Copied to clipboard

Ratish Puduppully, Mirella Lapata

Improving Generalization in Semantic Parsing by Increasing Natural Language Variation (2024.eacl-long)

Challenge:	Recent approaches to data-to-text generation adopt the encoder-decoder architecture . however, these models perform poorly at selecting appropriate content and ordering it coherently .
Approach:	They propose a neural model with a macro planning stage followed by a generation stage . they use data from databases of records, simulations of physical systems, accounting spreadsheets .
Outcome:	The proposed model outperforms baselines on two data-to-text benchmarks . it uses the encoderdecoder architecture and is compared with existing models .

Copied to clipboard

Irina Saparina, Mirella Lapata

Generating Query Focused Summaries from Query-Free Resources (2021.acl-long)

Challenge:	Existing approaches generate question reformulations via models trained on Spider or only introduce local changes. Existing methods generate question form reformulation but lack robustness.
Approach:	They use data augmentation to enhance the robustness of text-to-SQL parsers against natural language variations by generating more realistic and diverse questions.
Outcome:	The proposed model improves on the new spider dataset by using a few prompts.

Copied to clipboard

Yumo Xu, Mirella Lapata

Semantic graph parsing with recurrent neural network DAG grammars (D19-1)

Challenge:	Existing datasets are small for data-hungry neural architectures and are limited to evaluation purposes.
Approach:	They propose to decompose QFS into query modeling and conditional language modeling . they propose a Masked ROUGE Regression framework for evidence estimation and ranking .
Outcome:	The proposed model achieves state-of-the-art performance despite weak supervision.

Copied to clipboard

Federico Fancellu, Sorcha Gilroy, Adam Lopez, Mirella Lapata

What’s This Movie About? A Joint Neural Network Architecture for Movie Content Analysis (N18-1)

Challenge:	Semantic parsing is the task of mapping natural language to machine interpretable meaning representations.
Approach:	They propose a graph-aware sequence model that generates only well-formed graphs . their model is based on a multilingual semantic graphbank .
Outcome:	The proposed model yields competitive results in English and establishes the first results for German, Italian and Dutch.

Copied to clipboard

Philip John Gorinski, Mirella Lapata