Papers with SL
Contrastive Multi-document Question Generation (2021.eacl-main)
Copied to clipboard
Woon Sang Cho, Yizhe Zhang, Sudha Rao, Asli Celikyilmaz, Chenyan Xiong, Jianfeng Gao, Mengdi Wang, Bill Dolan
| Challenge: | Multi-document question generation focuses on generating a question that covers the common aspect of multiple documents, but a naive model trained only using the targeted document set may generate too generic questions that cover a larger scope than delineated by the document set. |
| Approach: | They propose a contrastive learning strategy where given ‘positive’ and ‘negative’ sets of documents, generate a question that is closely related to the ‘positive' set but far away from the ‘negative' set. |
| Outcome: | The proposed model significantly outperforms several strong baselines, as measured by automatic metrics and human evaluation. |
Multilingual Gloss-free Sign Language Translation: Towards Building a Sign Language Foundation Model (2025.acl-short)
Copied to clipboard
| Challenge: | Existing studies focus on translating a single SL into a spoken language (one-to-one SLT) however, multilingual SLT remains unexplored due to language conflicts and alignment difficulties across SLs and spoken languages. |
| Approach: | They propose a multilingual gloss-free model that can be used to translate a single SL into a spoken language and generate a token-level SL identification and spoken text. |
| Outcome: | The proposed model supports 10 SLs and handles one-to-one, many-to-1, and many- to-many SLT tasks. |
CASA-NLU: Context-Aware Self-Attentive Natural Language Understanding for Task-Oriented Chatbots (D19-1)
Copied to clipboard
| Challenge: | Prior work on contextual NLU has been limited in terms of the types of contextual signals used and the understanding of their impact on the model. |
| Approach: | They propose a context-aware self-attentive NLU model that uses multiple signals over a variable context window, such as previous intents, slots, dialog acts and utterances, in addition to the current user uttered. |
| Outcome: | The proposed model outperforms a baseline model on two conversational datasets yielding a gain of up to 7% on the IC task. |
The Troubling Emergence of Hallucination in Large Language Models - An Extensive Definition, Quantification, and Prescriptive Remediations (2023.emnlp-main)
Copied to clipboard
Vipula Rawte, Swagata Chakraborty, Agnibh Pathak, Anubhav Sarkar, S.M Towhidul Islam Tonmoy, Aman Chadha, Amit Sheth, Amitava Das
| Challenge: | Recent advances in Large Language Models have generated widespread acclaim, but hallucination has also emerged as a by-product. |
| Approach: | They propose a fine-grained discourse on profiling hallucination based on its degree, orientation, and category . they categorize hallucines into six types: acronym ambiguity, generated golem, virtual voice, geographic erratum, time wrap . |
| Outcome: | The proposed method categorizes hallucination into six types based on their degree, orientation, and category . |
Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to build a visual dialog (VD) Questioner do not provide explicit guidance for questioner to generate visually related and informative questions. |
| Approach: | They propose a Related entity enhanced Questioner that learns entity-based questioning strategy from human dialogs. |
| Outcome: | The proposed approach achieves state-of-the-art performance on image-guessing task and question diversity. |
Selective Prefix Tuning for Pre-trained Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pre-trained models are time-consuming and memory-inefficient. |
| Approach: | They propose a method that inserts learnable vectors into each Transformer layer . they propose SL to encourage diversity in prefix tokens . |
| Outcome: | Extensive experiments validate the effectiveness of Prefix Tuning in sentence and token classification tasks. |
ASCM: An Answer Space Clustered Prompting Method without Answer Engineering (2022.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models have shown a great impact on NLP tasks. |
| Approach: | They propose an answer space clustered prompting model and a synonym initialization method that automatically categorizes all answer tokens in a semantic-clustered embedding space. |
| Outcome: | Experiments show that the proposed method outperforms existing state-of-the-art methods in few-shot settings. |
Object-oriented Neural Programming (OONP) for Document Understanding (P18-1)
Copied to clipboard
| Challenge: | Object-oriented Neural Programming (OONP) is a framework for semantically parsing documents in domains. |
| Approach: | They propose a framework for semantically parsing documents in specific domains using OONP . OOPN parsers use a rich family of operations to represent the semantics of the document . |
| Outcome: | The proposed framework can learn to handle fairly complicated ontology with training data of modest sizes. |
Sequence Repetition Enhances Token Embeddings and Improves Sequence Labeling with Decoder-only Language Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Modern language models (LMs) are trained in autoregressive manner, conditioned on the prefix. sequence labeling (SL) tasks assign labels to each individual input token, naturally benefiting from bidirectional context. |
| Approach: | They explore sequence repetition (SR) as a less invasive alternative to decoder-only models . they show that increasing the number of repetitions does not degrade SL performance . |
| Outcome: | The proposed technique improves the quality of token-level embeddings and surpasses encoders and unmasked decoders. |
ZAP: An Open-Source Multilingual Annotation Projection Framework (L18-1)
Copied to clipboard
| Challenge: | Existing frameworks for annotation projection in parallel corpora limit reproducibility and comparison of experiments. |
| Approach: | They propose an open-source framework for annotation projection in parallel corpora . framework is Java-based and includes methods for preprocessing corpors, computations and visualization . |
| Outcome: | The proposed framework is designed for ease-of-use with lightweight APIs. |
Transfer-Free Data-Efficient Multilingual Slot Labeling (2023.emnlp-main)
Copied to clipboard
| Challenge: | Slot labeling (SL) is a key component of task-oriented dialogue systems . extending the system to any new language-domain-task configuration requires expensive data annotation . |
| Approach: | They propose a two-stage slot labeling approach which transforms sentence encoders into effective slot labels. |
| Outcome: | The proposed approach is especially effective for the most challenging transfer-free few-shot setups. |
Towards a new Ontology for Sign Languages (2022.lrec-1)
Copied to clipboard
| Challenge: | Linked Data (LD) compliant datasets for sign languages are not available in the LLOD cloud. |
| Approach: | They propose to create an ontology for representing constitutive elements of Sign Languages (SL) they propose to publish such data in the Linguistic Linked Open Data cloud. |
| Outcome: | The proposed ontology can be used to represent sign languages in the Linguistic Linked Open Data cloud. |
DGS-Fabeln-1: A Multi-Angle Parallel Corpus of Fairy Tales between German Sign Language and German Text (2024.lrec-main)
Copied to clipboard
Fabrizio Nunnari, Eleftherios Avramidis, Cristina España-Bonet, Marco González, Anna Hennes, Patrick Gebhard
| Challenge: | a parallel corpus of German text and videos containing fairy tales interpreted into the German Sign Language (DGS) is the first corpus filmed from 7 angles and one of the few sign language corpora globally which have been filmed simultaneously. |
| Approach: | They present a parallel corpus of German fairy tales interpreted by a native DGS signer. |
| Outcome: | The proposed corpus is the first semi-naturally expressed DGS that has been filmed from 7 angles and where the listener has been simultaneously filmed. |
Extending AZee with Non-manual Gesture Rules for French Sign Language (2024.lrec-main)
Copied to clipboard
| Challenge: | Currently, Sign Languages (SLs) are under-resourced and are difficult to develop. |
| Approach: | They propose to extend AZee to formally represent Sign Language discourses, but also to animate them with a virtual signer. |
| Outcome: | The proposed model allows to formally represent Sign Language discourses, but also to animate them with a virtual signer. |
Deep JSLC: A Multimodal Corpus Collection for Data-driven Generation of Japanese Sign Language Expressions (L18-1)
Copied to clipboard
| Challenge: | Existing technologies for CG-supported data display are not able to depict all relevant features of a natural signing sequence such as facial expression, spatial references or inter-sign movement. |
| Approach: | They collected a corpus of Japanese Sign Language sentences for deep neural network learning. |
| Outcome: | The proposed model could be used to train language features in Japanese Sign Language (JSL) |
Modeling French Sign Language: a proposal for a semantically compositional system (L18-1)
Copied to clipboard
| Challenge: | Several studies have proposed linguistic models to describe sign languages, but none have succeeded to describe the specificities of SL. |
| Approach: | They propose a linguistic approach to formalize the sign language (SL) they propose to take into account linguistic properties of the SL while respecting constraints of a modelisation process. |
| Outcome: | The proposed model takes into account linguistic properties of the sign language while respecting constraints of a modelisation process. |
Neural Machine Translation Methods for Translating Text to Sign Language Glosses (2023.acl-long)
Copied to clipboard
| Challenge: | State-of-the-art techniques common to low resource Machine Translation (MT) are applied to improve MT of spoken language text to Sign Language glosses. |
| Approach: | They propose to use data augmentation, semi-supervised Neural Machine Translation, transfer learning and multilingual NMT to improve MT of spoken language to Sign Language glosses. |
| Outcome: | The proposed models outperform previous work on two German SL corpora and are confirmed by human evaluation. |
Annotating a Fable in Italian Sign Language (LIS) (2020.lrec-1)
Copied to clipboard
| Challenge: | fables are short or medium-length stories with a moral and they generally have specific characteristics in SLs that are usually not to be found in spoken languages like Italian. |
| Approach: | They present work for automatic generation of a written text in Italian starting from glosses of fable in Italian Sign Language (LIS). |
| Outcome: | The proposed method was used to generate a written text in Italian starting from glosses of a fable in Italian Sign Language (LIS). |
Dicta-Sign-LSF-v2: Remake of a Continuous French Sign Language Dialogue Corpus and a First Baseline for Automatic Sign Language Processing (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing research on automatic Sign Language Processing (SLP) has focused on recognizing lexical signs, but other gestural units like iconic structures need to be recognized. |
| Approach: | They propose a public remake of the French Sign Language part of the Dicta-Sign corpus with clean annotations and a Convolutional-Recurrent Neural Network to train and test it. |
| Outcome: | The proposed version of the publicly available SL corpus Dicta-Sign is limited to its French Sign Language part and includes lexical and non-lexical annotations over 11 hours of video recording with 35000 manual units. |
GNN-SL: Sequence Labeling Based on Nearest Examples via GNN (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing sequence labeling algorithms can be decomposed into two parts . |
| Approach: | They propose a graph neural networks sequence labeling (GNN-SL) that augments the vanilla SL model output with similar tagging examples retrieved from the whole training set. |
| Outcome: | The proposed model performs well on three sequence labeling tasks. |
Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling (2024.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models excel in natural language understanding (NLU) tasks. |
| Approach: | They propose to apply layer-dependent removal of the causal mask (CM) during LLM fine-tuning to improve SL performance. |
| Outcome: | The proposed approach outperforms state-of-the-art SL models on IE tasks, while achieving state- of-the art results is unclear. |
DiffusionSL: Sequence Labeling via Tag Diffusion Process (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Sequence Labeling (SL) is a long-standing field of natural language processing. |
| Approach: | They propose a framework that utilizes a conditional discrete diffusion model for generating discrete tag data. |
| Outcome: | The proposed framework outperforms gpt-3.5-turbo on multiple benchmark datasets and tasks. |
Reinforcement Replaces Supervision: Query focused Summarization using Deep Reinforcement Learning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Query-focused Summarization (QfS) is a system that generates summaries from document(s) based on a query. |
| Approach: | They propose a Query-focused Summarization approach that uses a generalization of Reinforcement Learning (RL) for Natural Language Generation and a better semantic similarity reward. |
| Outcome: | The proposed approach improves on the ROUGE-L metric and in a benchmark dataset. |
Prompt-based Generation of Natural Language Explanations of Synthetic Lethality for Cancer Drug Discovery (2024.lrec-main)
Copied to clipboard
| Challenge: | Synthetic lethality (SL) is a genetic interaction where a single gene mutation allows cell survival, but simultaneous mutations in two genes lead to cell death. |
| Approach: | They propose a prompt-based pipeline for generating natural language explanations using a dataset derived from New Bing . |
| Outcome: | The proposed pipeline improves on existing biomedical language models in terms of text quality and explainability. |
HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing (2026.findings-acl)
Copied to clipboard
Chengyu Du, Xintao Wang, Aili Chen, Weiyuan Li, Rui Xu, Junteng Liu, Zishan Huang, Rong Tian, Zijun Sun, Yuhao Li, Liheng Feng, Deming Ding, Pengyu Zhao, Yanghua Xiao
| Challenge: | Existing models for LLM role-playing lack high-quality datasets with explicit reasoning traces and reliable reward signals aligned with human preferences. |
| Approach: | They propose a unified framework for cognitive-level persona simulation that strictly distinguishes characters’ first-person thinking processes from LLMs’ third-person reasoning. |
| Outcome: | The proposed framework outperforms the Qwen3-32B baseline model and achieves a 30.26% and 14.97% performance on the minimax benchmarks. |