Related papers: Using Linguistic Features to Improve the Generaliz…

Entity Coreference Resolution is the task of resolving all mentions in a document that refer to the same real world entity and is considered as one of the most difficult tasks in natural language understanding. It is of great importance for…

This paper presents a neural network classifier approach to detecting both within- and cross- document event coreference effectively using only event mention based features. Our approach does not (yet) rely on any event argument features…

Character linking, the task of linking mentioned people in conversations to the real world, is crucial for understanding the conversations. For the efficiency of communication, humans often choose to use pronouns (e.g., "she") or normal…

AI-text detectors achieve high accuracy on in-domain benchmarks, but often struggle to generalize across different generation conditions such as unseen prompts, model families, or domains. While prior work has reported these generalization…

Coreference resolution across multiple documents poses a significant challenge in natural language processing, particularly within the domain of knowledge graphs. This study introduces an innovative method aimed at identifying and resolving…

Enhancing the complex reasoning capabilities of Large Language Models (LLMs) attracts widespread attention. While reinforcement learning (RL) has shown superior performance for improving complex reasoning, its impact on cross-lingual…

Large language models (LLMs) have shown remarkable capabilities in natural language processing; however, they still face difficulties when tasked with understanding lengthy contexts and executing effective question answering. These…

Conversational search utilizes muli-turn natural language contexts to retrieve relevant passages. Existing conversational dense retrieval models mostly view a conversation as a fixed sequence of questions and responses, overlooking the…

Machine translation (MT) requires a wide range of linguistic capabilities, which current end-to-end models are expected to learn implicitly by observing aligned sentences in bilingual corpora. In this work, we ask: \emph{How well do MT…

While fine-tuned language models perform well on many tasks, they were also shown to rely on superficial surface features such as lexical overlap. Excessive utilization of such heuristics can lead to failure on challenging inputs. We…

Compositional generalization is the ability of a model to generalize to complex, previously unseen types of combinations of entities from just having seen the primitives. This type of generalization is particularly relevant to the semantic…

Guided by grammatical structure, words compose to form sentences, and guided by discourse structure, sentences compose to form dialogues and documents. The compositional aspect of sentence and discourse units is often overlooked by machine…

Language Models are the underpin of all modern Natural Language Processing (NLP) tasks. The introduction of the Transformers architecture has contributed significantly into making Language Modeling very effective across many NLP task,…

Since the first end-to-end neural coreference resolution model was introduced, many extensions to the model have been proposed, ranging from using higher-order inference to directly optimizing evaluation metrics using reinforcement…

There have been growing concerns regarding the out-of-domain generalization ability of natural language processing (NLP) models, particularly in question-answering (QA) tasks. Current synthesized data augmentation methods for QA are…

Coreference resolution in biomedical texts presents unique challenges due to complex domain-specific terminology, high ambiguity in mention forms, and long-distance dependencies between coreferring expressions. In this work, we present a…

Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However,…

Various neural-based methods have been proposed so far for joint mention detection and coreference resolution. However, existing works on coreference resolution are mainly dependent on filtered mention representation, while other spans are…

Linking pronominal expressions to the correct references requires, in many cases, better analysis of the contextual information and external knowledge. In this paper, we propose a two-layer model for pronoun coreference resolution that…

Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models (LLMs) beyond the training domain, while supervised fine-tuning (SFT) frequently leads to general capabilities forgetting.…