Related papers: Representation biases in sentence transformers
Widely used computer-aided translation (CAT) tools divide documents into segments such as sentences and arrange them in a side-by-side, spreadsheet-like view. We present the first controlled evaluation of these design choices on translator…
We present an introductory investigation into continuous-space vector representations of sentences. We acquire pairs of very similar sentences differing only by a small alterations (such as change of a noun, adding an adjective, noun or…
Models based on large-pretrained language models, such as S(entence)BERT, provide effective and efficient sentence embeddings that show high correlation to human similarity ratings, but lack interpretability. On the other hand, graph…
Sentence embeddings from transformer models encode in a fixed length vector much linguistic information. We explore the hypothesis that these embeddings consist of overlapping layers of information that can be separated, and on which…
The capabilities and limitations of BERT and similar models are still unclear when it comes to learning syntactic abstractions, in particular across languages. In this paper, we use the task of subordinate-clause detection within and across…
Although transformer-based Neural Language Models demonstrate impressive performance on a variety of tasks, their generalization abilities are not well understood. They have been shown to perform strongly on subject-verb number agreement in…
In most natural language inference problems, sentence representation is needed for semantic retrieval tasks. In recent years, pre-trained large language models have been quite effective for computing such representations. These models…
Traditional sentence embedding models encode sentences into vector representations to capture useful properties such as the semantic similarity between sentences. However, in addition to similarity, sentence semantics can also be…
There are several issues with the existing general machine translation or natural language generation evaluation metrics, and question-answering (QA) systems are indifferent in that context. To build robust QA systems, we need the ability…
Pretrained transformer-based models such as BERT have demonstrated state-of-the-art predictive performance when adapted into a range of natural language processing tasks. An open problem is how to improve the faithfulness of explanations…
This work describes experiments which probe the hidden representations of several BERT-style models for morphological content. The goal is to examine the extent to which discrete linguistic structure, in the form of morphological features…
Contrastive learning has shown great potential in unsupervised sentence embedding tasks, e.g., SimCSE. However, We find that these existing solutions are heavily affected by superficial features like the length of sentences or syntactic…
An important question concerning contextualized word embedding (CWE) models like BERT is how well they can represent different word senses, especially those in the long tail of uncommon senses. Rather than build a WSD system as in previous…
Semantic textual similarity is the task of estimating the similarity between the meaning of two texts. In this paper, we fine-tune transformer architectures for semantic textual similarity on the Semantic Textual Similarity Benchmark by…
Pre-trained contextualized language models such as BERT have shown great effectiveness in a wide range of downstream Natural Language Processing (NLP) tasks. However, the effective representations offered by the models target at each token…
In English semantic similarity tasks, classic word embedding-based approaches explicitly model pairwise "interactions" between the word representations of a sentence pair. Transformer-based pretrained language models disregard this notion,…
Question Answering (QA) is a task in natural language processing that has seen considerable growth after the advent of transformers. There has been a surge in QA datasets that have been proposed to challenge natural language processing…
We train multi-task autoencoders on linguistic tasks and analyze the learned hidden sentence representations. The representations change significantly when translation and part-of-speech decoders are added. The more decoders a model…
Active learning has been shown to be an effective way to alleviate some of the effort required in utilising large collections of unlabelled data for machine learning tasks without needing to fully label them. The representation mechanism…
Linguists have long held that a key aspect of natural language syntax is the recursive organization of language units into constituent structures, and research has suggested that current state-of-the-art language models lack an inherent…