Papers with neural approach
AMR-To-Text Generation with Graph Transformer (2020.tacl-1)
Copied to clipboard
| Challenge: | Abstract meaning representation (AMR)-to-text generation is challenging task for natural language processing. |
| Approach: | They propose a graph-to-sequence model that directly encodes AMR graphs and learns node representations. |
| Outcome: | The proposed model outperforms the current state-of-the-art neural approach by 1.5 BLEU points on LDC2015E86 and 4.8 BLUE points on the LDC2017T10 and achieves new state- of-the art performance. |
Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries (2021.acl-short)
Copied to clipboard
| Challenge: | despite advances in task-oriented and chit-chat based dialogue systems, many systems rely on static and unnatural responses. |
| Approach: | They propose a neural approach which generates contextually aware responses to user queries . they perform automatic and manual evaluations to demonstrate the efficacy of the system . |
| Outcome: | The proposed approach generates responses which are contextually aware with the user query and say no to the user. |
Neural OCR Post-Hoc Correction of Historical Corpora (2021.tacl-1)
Copied to clipboard
| Challenge: | Optical character recognition (OCR) is crucial for a deeper access to historical collections. |
| Approach: | They propose a neural approach based on a combination of recurrent (RNN) and deep convolutional network (ConvNet) to correct OCR transcription errors. |
| Outcome: | The proposed model reduces the word error rate of 32.3% by more than 89% on a historical book corpus in German language. |
Generating Repetitions with Appropriate Repeated Words (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing studies have focused on general response generation with neural network-based approaches, but none have addressed specific types of repetitions. |
| Approach: | They propose a weighted label smoothing method for explicitly learning which words to repeat during fine-tuning and a repetition scoring method that can output more appropriate repetitions during decoding. |
| Outcome: | The proposed method outperforms baselines in automatic and human evaluations on a pre-trained language model for generating repetitions. |
An Evaluation of Classifiers for Mapping Generative LLM Responses to Answer Options of Multiple-choice Questionnaires (2026.eacl-srw)
Copied to clipboard
| Challenge: | Large language models are used to generate multiple-choice style questionnaires that were originally intended for humans in persona simulations. |
| Approach: | They investigate the performance of smaller LLMs for mapping LLM outputs into the available answer options of multiple-choice questionnaires. |
| Outcome: | The proposed model underperforms on three datasets with differing answer option complexity. |
Neural Unsupervised Reconstruction of Protolanguage Word Forms (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for reconstructing ancient word forms use expectation-maximization . past work has used this method to predict simple phonological changes . |
| Approach: | They extend expectation-maximization to predict phonological changes between ancient word forms and their cognates in modern languages. |
| Outcome: | The proposed model reduces edit distance from the target word forms compared to previous methods. |
How to Avoid Sentences Spelling Boring? Towards a Neural Approach to Unsupervised Metaphor Generation (N19-1)
Copied to clipboard
| Challenge: | Existing approaches to generate metaphors rely on template-based or rule-based knowledge, which constrains the diversity of generated metaphors. |
| Approach: | They propose a neural approach to metaphor generation that uses wiki corpus to extract metaphorically used verbs and train a language model. |
| Outcome: | The proposed approach generates metaphors with good readability and creativity using wiki corpus and automatic metrics and human evaluations. |
ChEMU-Ref: A Corpus for Modeling Anaphora Resolution in the Chemical Domain (2021.eacl-main)
Copied to clipboard
| Challenge: | Using a novel annotation scheme, we identify anaphoric references in chemical patents and determine the chemical relation between linked entities. |
| Approach: | They propose a neural approach to anaphora resolution based on coreference and bridging links in chemical patents. |
| Outcome: | The proposed framework can be used to identify anaphoric references in chemical patents and determine the chemical relation between linked entities. |
Attention-Based Capsule Networks with Dynamic Routing for Relation Extraction (D18-1)
Copied to clipboard
| Challenge: | Existing neural networks focus on instance representation, and subsampling fails to retain precise spatial relationships between higher-level parts. |
| Approach: | They propose a neural approach based on capsule networks with attention mechanisms to extract relational information from a capsule. |
| Outcome: | The proposed method improves the precision of the predicted relations with different benchmarks. |
Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work on entity coreference resolution (CR) follows current trends in Deep Learning . traditional approaches do not make use of hierarchical representations of discourse structure . |
| Approach: | They propose to leverage automatically constructed discourse parse trees within a neural approach to generate anaphoric mentions. |
| Outcome: | The proposed model improves on two benchmark entity coreference-resolution datasets. |
Semi-Supervised Tri-Training for Explicit Discourse Argument Expansion (2020.lrec-1)
Copied to clipboard
| Challenge: | a novel application of semi-supervision for shallow discourse parsing is described . we focus on explicit discourse arguments, but we leave the sense selection aside . |
| Approach: | They propose a semi-supervised approach for shallow discourse parsing using sequence tagging. |
| Outcome: | The proposed approach improves performance by 2-10% in the first setting and by comparing the results with training relations. |
Data-to-Text Generation with Style Imitation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent approaches to data-to-text generation focus on improving content fidelity, but lack explicit control over writing styles. |
| Approach: | They propose a way to control writing styles by using existing sentences as "soft" templates . they conduct experiments in restaurants and sports domains to test their approach . |
| Outcome: | The proposed approach achieves stronger performance than a range of comparison methods. |
BengaliLCP: A Dataset for Lexical Complexity Prediction in the Bengali Texts (2024.lrec-main)
Copied to clipboard
| Challenge: | Lexical Complexity Prediction (LCP) is a task for predicting the complexity score of a word or phrase based on its context. |
| Approach: | They propose a deep neural approach to predict lexical complexity of Bengali tokens using an annotated dataset. |
| Outcome: | The proposed neural approach outperforms state-of-the-art models for Bengali language. |
Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for unsupervised text style transfer lack parallel data and difficulties in content preservation. |
| Approach: | They propose a neural approach to unsupervised text style transfer using non-parallel data. |
| Outcome: | The proposed approach can be trained end-to-end on two widely-used public datasets. |
Relation Extraction with Type-aware Map Memories of Word Dependencies (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on the dependency connections between words with limited attention paid to exploiting dependency types. |
| Approach: | They propose a neural approach for relation extraction with type-aware map memories . they map all associated words along with dependencies among them to memory slots . |
| Outcome: | The proposed approach achieves state-of-the-art on two English benchmark datasets. |
TWEETSPIN: Fine-grained Propaganda Detection in Social Media Using Multi-View Representations (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent studies on propaganda detection involve document and fragment-level analyses of news articles. |
| Approach: | They propose a neural approach to detect and categorize propaganda tweets across fine-grained categories . they use a dataset containing tweets weakly annotated with different propaganda techniques . |
| Outcome: | The proposed method outperforms benchmark methods and transfers knowledge to low-resource news domains. |
Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems (N19-1)
Copied to clipboard
| Challenge: | Existing methods to solve math word problems require accurate natural language understanding to bridge texts and math expressions. |
| Approach: | They propose a neural approach to automatically solve math word problems by operating symbols according to their semantic meanings in texts. |
| Outcome: | The proposed model outperforms state-of-the-art models and the best non-retrieval-based models over 10% accuracy in a Math23K dataset. |
Neural Quality Estimation of Grammatical Error Correction (D18-1)
Copied to clipboard
| Challenge: | Grammatical error correction systems are expected to correct most learners’ writing errors, but in practice they often produce spurious corrections and fail to correct many errors, thereby misleading learners. |
| Approach: | They propose to use supervised learning to estimate the quality of GEC output sentences to help instructors decide whether to correct the errors or ignore them altogether. |
| Outcome: | The proposed model improves on a feature-based baseline and shows that the state-of-the-art system can be improved when quality scores are used as features for re-ranking the N-best candidates. |
Neural Decipherment via Minimum-Cost Flow: From Ugaritic to Linear B (P19-1)
Copied to clipboard
| Challenge: | Existing methods for decipherment of lost languages are limited by limited data and scarce quantities of ancient text. |
| Approach: | They propose a neural approach for automatic decipherment of lost languages . they use an expressive sequence-to-sequence model to capture character-level correspondences between cognates . |
| Outcome: | The proposed approach improves on the decipherment of Ugaritic and Linear B in ancient Greek . the proposed approach is highly customized for a given language pair and does not generalize to other lost languages. |
Learning to Generate Examples for Semantic Processing Tasks (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent data augmentation techniques can help to deal with low resource settings, such as BERT, but they can hurt the results. |
| Approach: | They propose a neural approach to automatically learn to generate new examples using a pre-trained sequence-to-sequence model. |
| Outcome: | The proposed approach outperforms existing methods on text classification and natural language inference tasks by 10%. |
Semantic Relatedness Based Re-ranker for Text Spotting (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to text spotting are limited by semantic similarity, but they can be useful for other tasks. |
| Approach: | They propose a neural approach to learn semantic relatedness from existing sentences. |
| Outcome: | The proposed approach outperforms existing approaches when applied to a text spotting task. |
Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation (P19-1)
Copied to clipboard
| Challenge: | IRNet synthesizes SQL queries in an end-to-end manner, but it yields unsatisfactory performance on public benchmarks. |
| Approach: | They propose a neural approach called IRNet for complex and cross-domain Text-to-SQL. |
| Outcome: | IRNet achieves 46.7% accuracy on the Spider benchmark, a 19.5% improvement over state-of-the-art approaches. |
Simulating ASR errors for training SLU systems (L18-1)
Copied to clipboard
| Challenge: | Existing methods to simulate automatic speech recognition errors from manual transcriptions are not available during training of the SLU model. |
| Approach: | They propose to use acoustic and linguistic word embeddings to define a similarity measure between words to predict ASR confusions. |
| Outcome: | The proposed method significantly improves the performance of spoken language understanding systems. |
Cross-lingual neural fuzzy matching for exploiting target-language monolingual corpora in computer-aided translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | CAT tools based on translation memories (TMs) are limited in their use for a number of translation tasks due to the limited availability of in-domain TMs. |
| Approach: | They propose a neural approach to exploit in-domain TMs and in-target-language (TL) monolingual corpora to exploit CAT tools. |
| Outcome: | The proposed approach exploits in-domain TMs and in-target-language (TL) monolingual corpora and increases translation proposals on four language pairs. |
MovieChats: Chat like Humans in a Closed Domain (2020.emnlp-main)
Copied to clipboard
| Challenge: | Currently, open-domain chatbots are far from satisfactory. |
| Approach: | They propose a unified, readily scalable neural approach which reconciles all subtasks like intent prediction and knowledge retrieval. |
| Outcome: | The proposed approach outperforms commercial systems replying on complex rules on static and interactive tests and shows that the results are remarkably good. |
Thematic Fit Bits: Annotation Quality and Quantity Interplay for Event Participant Representation (2022.lrec-1)
Copied to clipboard
| Challenge: | linguistically machine-annotated large corpus requires a large burden of labeled data. |
| Approach: | They compare linguistically machine-annotated large corpus output with higher-quality taggers to model thematic fit using a high-performing neural approach. |
| Outcome: | The proposed model shows that quality improves with training size, but plateaus or declines with size. |
A Rewriting Approach for Gender Inclusivity in Portuguese (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent research has focused on gender-inclusive and gender-neutral language . however, current approaches to gender- neutral rewriting for gendered languages rely on large datasets . |
| Approach: | They propose a rule-based and a neural-based tool for gender-neutral rewriting for Portuguese, a heavily gendered Romance language. |
| Outcome: | The proposed model fine-tunes large multilingual machine translation models on examples generated by the rule-based model. |
NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender Neutral Alternatives (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent years have seen an increasing need for gender-neutral and inclusive language. |
| Approach: | They propose a rule-based and a neural approach to gender-neutral rewriting for English . they use manually curated synthetic and natural data to train a rewriter . |
| Outcome: | The proposed approach improves on the rule-based approach with word error rates below 0.18% on synthetic, in-domain and out-domain test sets. |
SConE: Simplified Cone Embeddings with Symbolic Operators for Complex Logical Queries (2023.findings-acl)
Copied to clipboard
| Challenge: | Current geometric-based methods depend on the neural approach to model FOL operators . empirical evidence for explainability is challenging . |
| Approach: | They propose to model conjunction operators using a symbolic modeling approach . they propose to emphasize the essential role of relation projection operator . |
| Outcome: | The proposed method improves answering complex logical queries over previous models. |
Unsupervised Argumentation Mining in Student Essays (2020.lrec-1)
Copied to clipboard
| Challenge: | State-of-the-art argumentation mining systems rely on annotated training data and are supervised, thus relying on an annotation of the components and relationships between them. |
| Approach: | They propose to bootstrap from a small set of argument components automatically identified using simple heuristics in combination with reliable contextual cues. |
| Outcome: | The proposed approach outperforms two supervised baselines and achieves 73.5-83.7% of the performance of a state-of-the-art neural approach. |