Related papers: Multi-Task Learning for Conversational Question An…

We study how to leverage off-the-shelf visual and linguistic data to cope with out-of-vocabulary answers in visual question answering task. Existing large-scale visual datasets with annotations such as image class labels, bounding boxes and…

Large Language Models (LLMs) have demonstrated amazing capabilities in language generation, text comprehension, and knowledge reasoning. While a single powerful model can already handle multiple tasks, relying on a single perspective can…

When answering a question, people often draw upon their rich world knowledge in addition to the particular context. Recent work has focused primarily on answering questions given some relevant document or context, and required very little…

This study aims to explore the performance improvement method of large language models based on GPT-4 under the multi-task learning framework and conducts experiments on two tasks: text classification and automatic summary generation.…

Large language models (LLMs) achieve strong average performance yet remain unreliable at the instance level, with frequent hallucinations, brittle failures, and poorly calibrated confidence. We study reliability through the lens of…

Multi-party learning provides solutions for training joint models with decentralized data under legal and practical constraints. However, traditional multi-party learning approaches are confronted with obstacles such as system…

With the development of pre-trained language models, remarkable success has been witnessed in dialogue understanding (DU). However, current DU approaches usually employ independent models for each distinct DU task without considering shared…

Large language models show compelling performance on reasoning tasks but they tend to perform much worse in languages other than English. This is unsurprising given that their training data largely consists of English text and instructions.…

Task semantics can be expressed by a set of input-output examples or a piece of textual instruction. Conventional machine learning approaches for natural language processing (NLP) mainly rely on the availability of large-scale sets of…

A long-standing challenge in coreference resolution has been the incorporation of entity-level information - features defined over clusters of mentions instead of mention pairs. We present a neural network based coreference system that…

This paper proposes a new principled multi-task representation learning framework (InfoMTL) to extract noise-invariant sufficient representations for all tasks. It ensures sufficiency of shared representations for all tasks and mitigates…

Multi-entity question answering (MEQA) represents significant challenges for large language models (LLM) and retrieval-augmented generation (RAG) systems, which frequently struggle to consolidate scattered information across diverse…

Multi-table entity matching (MEM) addresses the limitations of dual-table approaches by enabling simultaneous identification of equivalent entities across multiple data sources without unique identifiers. However, existing methods relying…

Document-level joint entity and relation extraction is a challenging information extraction problem that requires a unified approach where a single neural network performs four sub-tasks: mention detection, coreference resolution, entity…

Multi-task learning has recently become a very active field in deep learning research. In contrast to learning a single task in isolation, multiple tasks are learned at the same time, thereby utilizing the training signal of related tasks…

The cost of annotating training data has traditionally been a bottleneck for supervised learning approaches. The problem is further exacerbated when supervised learning is applied to a number of correlated tasks simultaneously since the…

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

Human knowledge is collectively encoded in the roughly 6500 languages spoken around the world, but it is not distributed equally across languages. Hence, for information-seeking question answering (QA) systems to adequately serve speakers…

Spoken language understanding has been addressed as a supervised learning problem, where a set of training data is available for each domain. However, annotating data for each domain is both financially costly and non-scalable so we should…

Multi-intent Spoken Language Understanding has great potential for widespread implementation. Jointly modeling Intent Detection and Slot Filling in it provides a channel to exploit the correlation between intents and slots. However, current…