Articles

AbstractThe present article discusses how to improve translation quality when using limited training data to translate towards morphologically rich languages. The starting point is a neural MT system, used to train translation models, using solely publicly available parallel data. An initial analysis of the translation output has shown that quality …...

Abstract(CITATION) argued for using random splits rather than standard splits in NLP experiments. We argue that random splits, like standard splits, lead to overly optimistic performance estimates. We can also split data in biased or adversarial ways, e.g., training on short sentences and evaluating on long ones. Biased sampling has …...

AbstractIn this work, we consider the problem of uncertainty estimation for Transformer-based models. We investigate the applicability of uncertainty estimates based on dropout usage at the inference stage (Monte Carlo dropout). The series of experiments on natural language understanding tasks shows that the resulting uncertainty estimates improve the quality of …...

AbstractGiven the potential misuse of recent advances in synthetic text generation by language models (LMs), it is important to have the capacity to attribute authorship of synthetic text. While stylometric organic (i.e., human written) authorship attribution has been quite successful, it is unclear whether similar approaches can be used to …...

AbstractFine-tuning a large language model on downstream tasks has become a commonly adopted process in the Natural Language Processing (NLP) (CITATION). However, such a process, when associated with the current transformer-based (CITATION) architectures, shows several limitations when the target task requires to reason with long documents. In this work, we …...

AbstractIn this paper, we challenge the assumption that political ideology is inherently built into text by presenting an investigation into the impact of experiential factors on annotator perceptions of political ideology. We construct an annotated corpus of U.S. political discussion, where in addition to ideology labels for texts, annotators provide …...

AbstractIn this work, we explore joint energy-based model (EBM) training during the finetuning of pretrained text encoders (e.g., Roberta) for natural language understanding (NLU) tasks. Our experiments show that EBM training can help the model reach a better calibration that is competitive to strong baselines, with little or no loss …...

AbstractSpeech disfluencies are prevalent in spontaneous speech. The rising popularity of voice assistants presents a growing need to handle naturally occurring disfluencies. Semantic parsing is a key component for understanding user utterances in voice assistants, yet most semantic parsing research to date focuses on written text. In this paper, we …...

AbstractPretrained transformer-based models, such as BERT and its variants, have become a common choice to obtain state-of-the-art performances in NLP tasks. In the identification of Adverse Drug Events (ADE) from social media texts, for example, BERT architectures rank first in the leaderboard. However, a systematic comparison between these models has …...

AbstractDialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information etc. With the increasing need to deploy such systems in new domains, solving the problem of zero/few-shot DST has become necessary. There has been a rising trend …...

AbstractWhen responding to a disaster, humanitarian experts must rapidly process large amounts of secondary data sources to derive situational awareness and guide decision-making. While these documents contain valuable information, manually processing them is extremely time-consuming when an expedient response is necessary. To improve this process, effective summarization models are a …...

AbstractAssessing the quality of arguments and of the claims the arguments are composed of has become a key task in computational argumentation. However, even if different claims share the same stance on the same topic, their assessment depends on the prior perception and weighting of the different aspects of the …...

AbstractAnnotating training data for sequence tagging of texts is usually very time-consuming. Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the necessary annotation budget. We are the first to thoroughly investigate this powerful combination for the sequence tagging …...

AbstractModern neural approaches to dependency parsing are trained to predict a tree structure by jointly learning a contextual representation for tokens in a sentence, as well as a head–dependent scoring function. Whereas this strategy results in high performance, it is difficult to interpret these representations in relation to the geometry …...

AbstractMany data sets (e.g., reviews, forums, news, etc.) exist parallelly in multiple languages. They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models. Models have to be either single-language or suffer from a huge, but extremely sparse vocabulary. Both issues can …...

AbstractPrevious research on target-dependent sentiment classification (TSC) has mostly focused on reviews, social media, and other domains where authors tend to express sentiment explicitly. In this paper, we investigate TSC in news articles, a much less researched TSC domain despite the importance of news as an essential information source in …...

AbstractWe address the problem of unsupervised abstractive summarization of collections of user generated reviews through self-supervision and control. We propose a self-supervised setup that considers an individual document as a target summary for a set of similar documents. This setting makes training simpler than previous approaches by relying only on …...

AbstractWe present WiC-TSV, a new multi-domain evaluation benchmark for Word Sense Disambiguation. More specifically, we introduce a framework for Target Sense Verification of Words in Context which grounds its uniqueness in the formulation as binary classification task thus being independent of external sense inventories, and the coverage of various domains. …...

AbstractSentence Compression is the task of generating a shorter, yet grammatical, version of a given sentence, preserving the essence of the original sentence. This paper proposes a Black-Box Optimizer for Compression (B-BOC): given a black-box compression algorithm and assuming not all sentences need be compressed – find the best candidates …...

AbstractPretrained language models have been suggested as a possible alternative or complement to structured knowledge bases. However, this emerging LM-as-KB paradigm has so far only been considered in a very limited setting, which only allows handling 21k entities whose name is found in common LM vocabularies. Furthermore, a major benefit …...