Related papers: Did the Models Understand Documents? Benchmarking …
Long-sequence transformers are designed to improve the representation of longer texts by language models and their performance on downstream document-level tasks. However, not much is understood about the quality of token-level predictions…
It is well-known that document context is vital for resolving a range of translation ambiguities, and in fact the document setting is the most natural setting for nearly all translation. It is therefore unfortunate that machine translation…
Document-level translation models are usually evaluated using general metrics such as BLEU, which are not informative about the benefits of context. Current work on context-aware evaluation, such as contrastive methods, only measure…
Document-level relation extraction is to extract relation facts from a document consisting of multiple sentences, in which pronoun crossed sentences are a ubiquitous phenomenon against a single sentence. However, most of the previous works…
In this work, we aim at developing an extractive summarizer in the multi-document setting. We implement a rank based sentence selection using continuous vector representations along with key-phrases. Furthermore, we propose a model to…
Document-level Relation Extraction (DRE) aims to recognize the relations between two entities. The entity may correspond to multiple mentions that span beyond sentence boundary. Few previous studies have investigated the mention…
Understanding visually situated language requires interpreting complex layouts of textual and visual elements. Pre-processing tools, such as optical character recognition (OCR), can map document image inputs to textual tokens, then large…
Ranking models are the main components of information retrieval systems. Several approaches to ranking are based on traditional machine learning algorithms using a set of hand-crafted features. Recently, researchers have leveraged deep…
Compared to sentence-level systems, document-level neural machine translation (NMT) models produce a more consistent output across a document and are able to better resolve ambiguities within the input. There are many works on…
Two of the most fundamental challenges in Natural Language Understanding (NLU) at present are: (a) how to establish whether deep learning-based models score highly on NLU benchmarks for the 'right' reasons; and (b) to understand what those…
Accurate prediction of human behavior is essential for robust and safe human-AI collaboration. However, existing approaches for modeling people are often data-hungry and brittle because they either make unrealistic assumptions about…
Neural machine translation (NMT) has arguably achieved human level parity when trained and evaluated at the sentence-level. Document-level neural machine translation has received less attention and lags behind its sentence-level…
Context information around words helps in determining their actual meaning, for example "networks" used in contexts of artificial neural networks or biological neuron networks. Generative topic models infer topic-word distributions, taking…
With over 200 million published academic documents and millions of new documents being written each year, academic researchers face the challenge of searching for information within this vast corpus. However, existing retrieval systems…
Rule-based information extraction has lately received a fair amount of attention from the database community, with several languages appearing in the last few years. Although information extraction systems are intended to deal with…
Continual relation extraction (CRE) aims to solve the problem of catastrophic forgetting when learning a sequence of newly emerging relations. Recent CRE studies have found that catastrophic forgetting arises from the model's lack of…
While recent large language models (LLMs) improve on various question answering (QA) datasets, it remains difficult for a single model to generalize across question types that require distinct reasoning abilities. We provide empirical…
Recent research suggests that neural machine translation achieves parity with professional human translation on the WMT Chinese--English news translation task. We empirically test this claim with alternative evaluation protocols,…
Reward Models (RMs) are crucial for aligning language models with human preferences. Currently, the evaluation of RMs depends on measuring accuracy against a validation set of manually annotated preference data. Although this method is…
Detecting factual inconsistency for long document summarization remains challenging, given the complex structure of the source article and long summary length. In this work, we study factual inconsistency errors and connect them with a line…