相关论文: Assigning Grammatical Relations with a Back-off Mo…

We propose a Bayesian model of unsupervised semantic role induction in multiple languages, and use it to explore the usefulness of parallel corpora for this task. Our joint Bayesian model consists of individual models for each language plus…

We develop the multilingual topic model for unaligned text (MuTo), a probabilistic model of text that is designed to analyze corpora composed of documents in two languages. From these documents, MuTo uses stochastic EM to simultaneously…

Transformer-based language models have achieved remarkable success in few-shot in-context learning and drawn a lot of research interest. However, these models' performance greatly depends on the choice of the example prompts and also has…

Syntactic features play an essential role in identifying relationship in a sentence. Previous neural network models often suffer from irrelevant information introduced when subjects and objects are in a long distance. In this paper, we…

Available corpora for Argument Mining differ along several axes, and one of the key differences is the presence (or absence) of discourse markers to signal argumentative content. Exploring effective ways to use discourse markers has…

We study the problem of classification with a reject option for a fixed predictor, applicable in natural language processing. We introduce a new problem formulation for this scenario, and an algorithm minimizing a new surrogate loss…

In the present paper we show that distributional information is particularly important when considering concept availability under implicit language learning conditions. Based on results from different behavioural experiments we argue that…

Contrastive learning has proven instrumental in learning unbiased representations of data, especially in complex environments characterized by high-cardinality and high-dimensional sensitive information. However, existing approaches within…

Relational databases are valuable resources for learning novel and interesting relations and concepts. In order to constraint the search through the large space of candidate definitions, users must tune the algorithm by specifying a…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

Bilingual sequence models improve phrase-based translation and reordering by overcoming phrasal independence assumption and handling long range reordering. However, due to data sparsity, these models often fall back to very small context…

The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word…

Probing and enhancing large language models' reasoning capacity remains a crucial open question. Here we re-purpose the reverse dictionary task as a case study to probe LLMs' capacity for conceptual inference. We use in-context learning to…

In natural language the intended meaning of a word or phrase is often implicit and depends on the context. In this work, we propose a simple yet effective method for sentiment analysis using contextual embeddings and a self-attention…

The naive approach to annotation projection is not effective to project discourse annotations from one language to another because implicit discourse relations are often changed to explicit ones and vice-versa in the translation. In this…

This paper introduces a new type of unsupervised learning algorithm, based on the alignment of sentences and Harris's (1951) notion of interchangeability. The algorithm is applied to an untagged, unstructured corpus of natural language…

This thesis investigates how the sub-structure of words can be accounted for in probabilistic models of language. Such models play an important role in natural language processing tasks such as translation or speech recognition, but often…

We introduce Trans-gram, a simple and computationally-efficient method to simultaneously learn and align wordembeddings for a variety of languages, using only monolingual data and a smaller set of sentence-aligned data. We use our new…

The majority of existing post-hoc explanation approaches for machine learning models produce independent, per-variable feature attribution scores, ignoring a critical inherent characteristics of homogeneously structured data, such as visual…

Third-person singular pronouns have long been used to study stereotypical biases in language models and to test their abilities to reason about reference. More recently, the interplay between reasoning and bias has been investigated with…