Papers with matching

25 papers
One Time of Interaction May Not Be Enough: Go Deep with an Interaction-over-Interaction Network for Response Selection in Dialogues (P19-1)

Copied to clipboard

Challenge: Currently, retrieval-based dialogues are performed in shallow ways . a recent study investigated the problem of context-response matching in open-domain .
Approach: They propose a model that lets utterance-response interaction go deep by stacking interaction blocks.
Outcome: The proposed model outperforms state-of-the-art methods on three benchmark data sets.
Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension (D19-58)

Copied to clipboard

Challenge: Experimental results show that unified model outperforms other models that treat encoding and matching separately.
Approach: They evaluate a unified model with Transformer layers for machine reading comprehension . they find that the model learns different modeling strategies compared with previous models .
Outcome: The unified model outperforms models with Transformer layers on the machine reading comprehension task.
Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching (2025.coling-main)

Copied to clipboard

Challenge: Entity matching (EM) is a critical step in entity resolution (ER).
Approach: They propose a method that incorporates record interactions from different perspectives.
Outcome: The proposed framework improves on 8 ER datasets and 10 LLMs and achieves higher efficiency and effectiveness.
The Dog the Cat Chased Stumped the Model: Measuring When Language Models Abandon Structure for Shortcuts (2026.eacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) can explain quantum mechanics and write sophisticated code, yet fail to parse sentences like "The cat that the mouse feared chased meowed"
Approach: They propose a framework to distinguish structural understanding from semantic pattern matching . they use a set of 9,720 comprehension questions on center-embedded sentences .
Outcome: a new framework shows that models lose performance when they abandon structural analysis for semantic associations.
LATEX-Numeric: Language Agnostic Text Attribute Extraction for Numeric Attributes (2021.naacl-industry)

Copied to clipboard

Challenge: Existing methods for training numeric attributes are based on manual labeling and distant supervision leads to incomplete training annotations.
Approach: They propose a multi-task learning architecture to deal with missing attribute values in training data, removing dependency on manual annotations.
Outcome: The proposed framework improves on 20 numeric attributes extracted from 5 product categories and 3 english marketplaces with language-agnostic performance.
Valet: Rule-Based Information Extraction for Rapid Deployment (2022.lrec-1)

Copied to clipboard

Challenge: a number of machine learning models can be trained to perform sentence-level information extraction at accuracies ranging from strong to adequate.
Approach: They propose a Python framework for rule-based information extraction that allows for complex matching.
Outcome: The proposed framework can be used to perform rule-based information extraction on examples.
Pretraining and Finetuning Language Models on Geospatial Networks for Accurate Address Matching (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing approaches to address matching and building authoritative address catalogues are limited in data quality and require labeling effort to develop accurate models.
Approach: They propose to view addresses as an address graph and curate inputs by placing geospatially linked addresses in the same context.
Outcome: The proposed framework improves address matching and fine-tuning language models.
Aspect-based Key Point Analysis for Quantitative Summarization of Reviews (2024.findings-eacl)

Copied to clipboard

Challenge: Existing studies on review summarization use only major opinions, but ignore minority opinions and fail to quantify opinion prevalence.
Approach: They propose a framework for quantitative review summarization using aspect-based key point analysis (ABKPA) they use aspect-basic sentiment analysis to automatically annotate silver labels for matching aspect-sentiment pairs .
Outcome: The proposed framework outperforms state-of-the-art baselines on Yelp reviews on five business categories.
A BERT-based Dual Embedding Model for Chinese Idiom Prediction (2020.coling-main)

Copied to clipboard

Challenge: Chinese idioms are special fixed phrases whose meanings are often highly idiomatic and non-compositional.
Approach: They propose to use a BERT-based dual embedding model to encode contextual words and learn dual embeds of the idioms.
Outcome: The proposed model performs better than the existing state of the art on a Chinese idiom cloze dataset.
Transformer-based Models for Long-Form Document Matching: Challenges and Empirical Analysis (2023.findings-eacl)

Copied to clipboard

Challenge: Recent advances in the area of long document matching have primarily focused on using transformer-based models for long document encoding and matching.
Approach: They propose to use simple neural models and simple embeddings to improve document matching by taking significantly less training time, energy, and memory.
Outcome: The proposed models outperform the more complex BERT-based models while taking significantly less training time, energy, and memory.
Optimal Partial Transport Based Sentence Selection for Long-form Document Matching (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for document matching are limited by the partial nature of the sentence-level matching signals.
Approach: They propose a matching approach that equips existing document matching models with an Optimal Partial Transport component, namely OPT-Match, which selects the key sentences that play a major role in matching.
Outcome: The proposed approach outperforms existing models on four publicly available datasets and the key sentences selected by it are consistent with human-provided rationales.
BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Currently, pre-trained language model (PLM) based metrics are widely adopted in text generation tasks.
Approach: They propose to use PLMs to encode stereotypical societal biases in PLM-based metrics . they show that popular metrics exhibit higher social bias than traditional metrics based on 6 attributes .
Outcome: The proposed method shows that PLM-based metrics exhibit higher social bias than traditional metrics on 6 attributes.
BERT Is Not The Count: Learning to Match Mathematical Statements with Proofs (2023.eacl-main)

Copied to clipboard

Challenge: Existing work on mathematical article analysis uses natural language processing to solve complex mathematical articles.
Approach: They propose a bilinear similarity model and two decoding methods to match statements to proofs effectively.
Outcome: The proposed model matches proofs to statements without being aware of proofs, but it follows a relatively shallow symbolic analysis and matching to achieve that performance.
Original Semantics-Oriented Attention and Deep Fusion Network for Sentence Matching (D19-1)

Copied to clipboard

Challenge: Sentence matching is a key issue in natural language inference and paraphrase identification.
Approach: They propose a semantics-oriented attention and deep fusion network (OSOA-DFN) that is oriented to the original semantic representation of another sentence and propagates attention information at each matching layer.
Outcome: The proposed model can model sentence matching more precisely on three sentence matching benchmark datasets.
EDIS: Entity-Driven Image Search over Multimodal Web Content (2023.emnlp-main)

Copied to clipboard

Challenge: Existing image retrieval methods require large datasets and a large candidate set.
Approach: They propose a news-domain dataset for cross-modal image search with 1 million web images . they propose combining multimodal image-text pairs with a million candidates .
Outcome: The proposed dataset challenges state-of-the-art methods with dense entities and the large-scale candidate set.
Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Recent studies show that Large language models struggle with handling long token sequences due to limited training context size.
Approach: They propose a single-stage continual pretraining method to equip LLMs with long context modeling capabilities.
Outcome: The proposed method outperforms existing methods on 4 language modeling benchmarks.
CNM: An Interpretable Complex-valued Network for Matching (N19-1)

Copied to clipboard

Challenge: Existing work on quantum physics models language understanding using quantum probability .
Approach: They propose a quantum-theoretic framework that unifies different linguistic units in a single complex-valued vector space and a complex-valuable network for semantic matching.
Outcome: The proposed framework achieves comparable performances to strong CNN and RNN baselines on two benchmarking question answering (QA) datasets.
How to Talk to Language Models: Serialization Strategies for Structured Entity Matching (2025.findings-naacl)

Copied to clipboard

Challenge: Entity matching (EM) identifies whether two data records refer to the same entity . however, its performance heavily depends on how structured entities are “talked” through serialized text.
Approach: They propose a novel serialization scheme for entities with complex relations in knowledge graphs based on random walks and use open-source LLMs to encode sampled semantic walks for matching.
Outcome: The proposed scheme achieves leading performance on EM in canonical and heterogeneous KGs.
Embedding Meta-Textual Information for Improved Learning to Rank (2020.coling-main)

Copied to clipboard

Challenge: a neural representation learning approach has not been extended to meta-textual information that is readily available for many IR tasks.
Approach: They propose a framework that learns embeddings for meta-textual categories and optimizes a pairwise ranking objective for improved matching based on combined embedds of textual and meta-tactile information.
Outcome: The proposed framework improves cross-lingual retrieval in the Wikipedia domain and Patent domain.
HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning (2022.findings-emnlp)

Copied to clipboard

Challenge: Temporal Knowledge Graphs (TKGs) store facts as triples in the form of subject, relation, object, timestamps.
Approach: They propose a Temporal Knowledge Graph (TKG) model that extends each triple with a timestamp to describe dynamic facts.
Outcome: The proposed model improves on six benchmark datasets with up to 5.6% performance improvement compared to the state-of-the-art models.
Neural Graph Matching Networks for Chinese Short Text Matching (2020.acl-main)

Copied to clipboard

Challenge: Chinese word segmentation can be erroneous, ambiguous or inconsistent, causing performance problems.
Approach: They propose a sentence matching framework that uses paired word lattices as input instead of a character sequence.
Outcome: The proposed framework outperforms the state-of-the-art short text matching models on two Chinese datasets.
Overcoming the Long Tail Problem: A Case Study on CO2-Footprint Estimation of Recipes using Information Retrieval (L18-1)

Copied to clipboard

Challenge: a particular challenge is the "long tail problem" that arises with the large diversity of possible ingredients.
Approach: They propose methods that use information retrieval methods for automatic calculation of CO2-footprints of cooking recipes.
Outcome: The proposed methods are generalizable to other use cases where a numerical value has to be calculated based on a list of textual elements.
A Semantic Filter Based on Relations for Knowledge Graph Completion (2021.emnlp-main)

Copied to clipboard

Challenge: Knowledge graph embedding is a new form of knowledge graphing that allows for better link prediction.
Approach: They propose to use relational embedding to fit symmetry/antisymmetry and combination relationships.
Outcome: The proposed model can fit symmetry/antisymmetry and combination relationships.
Multi-Granularity Fusion Text Semantic Matching Based on WoBERT (2024.lrec-main)

Copied to clipboard

Challenge: Existing text-matching methods struggle with semantic nuances in short texts . a novel approach to improve text semantic matching is being developed .
Approach: They propose a multi-granularity fusion model that harnesses a pre-trained language model to capture text semantic nuances.
Outcome: The proposed model improves on Chinese short text matching datasets compared to traditional methods . the proposed model captures individual text semantic nuances and improves accuracy .
A Text-Based Recommender System that Leverages Explicit Affective State Preferences (2025.emnlp-main)

Copied to clipboard

Challenge: Existing systems that leverage user preferences that are implicit in user-item rating histories can be slow to track changes in user preferences and imprecise for users with diverse preferences.
Approach: They propose a novel recommendation task that leverages a wide range of affective states sought explicitly by the user to identify items that induce those affective state.
Outcome: The proposed model can leverage a wide range of affective states sought explicitly by the user to identify items likely to induce those affective state.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations