Related papers: Natural Language Multitasking: Analyzing and Impro…

We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence…

TV subtitles are a rich source of transcriptions of many types of speech, ranging from read speech in news reports to conversational and spontaneous speech in talk shows and soaps. However, subtitles are not verbatim (i.e. exact)…

Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of them. The typical recipe involves: (i) training a deep,…

Previous works have demonstrated the effectiveness of utilising pre-trained sentence encoders based on their sentence representations for meaning comparison tasks. Though such representations are shown to capture hidden syntax structures,…

Unsupervised sentence embeddings task aims to convert sentences to semantic vector representations. Most previous works directly use the sentence representations derived from pretrained language models. However, due to the token bias in…

We consider multi-class classification where the predictor has a hierarchical structure that allows for a very large number of labels both at train and test time. The predictive power of such models can heavily depend on the structure of…

Neural language models learn word representations, or embeddings, that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models, a recently-developed class of neural…

Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…

Embeddings play an important role in end-to-end solutions for multi-modal language processing problems. Although there has been some effort to understand the properties of single-modality embedding spaces, particularly that of text, their…

In this paper, our goal is to investigate to what degree multilingual pretrained language models capture cross-linguistically valid abstract linguistic representations. We take the approach of developing curated synthetic data on a large…

Recent works show that discourse analysis benefits from modeling intra- and inter-sentential levels separately, where proper representations for text units of different granularities are desired to capture both the meaning of text units and…

While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector…

We study the evolution of latent space in fine-tuned NLP models. Different from the commonly used probing-framework, we opt for an unsupervised method to analyze representations. More specifically, we discover latent concepts in the…

We introduce a neural semantic parser that converts natural language utterances to intermediate representations in the form of predicate-argument structures, which are induced with a transition system and subsequently mapped to target…

We decompose multimodal translation into two sub-tasks: learning to translate and learning visually grounded representations. In a multitask learning framework, translations are learned in an attention-based encoder-decoder, and grounded…

Fine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models. Very little is,…

Bilingual word embeddings have been widely used to capture the similarity of lexical semantics in different human languages. However, many applications, such as cross-lingual semantic search and question answering, can be largely benefited…

This paper extends the task of probing sentence representations for linguistic insight in a multilingual domain. In doing so, we make two contributions: first, we provide datasets for multilingual probing, derived from Wikipedia, in five…

Due to their similarity-based learning objectives, pretrained sentence encoders often internalize stereotypical assumptions that reflect the social biases that exist within their training corpora. In this paper, we describe several kinds of…

Context-aware Machine Translation aims to improve translations of sentences by incorporating surrounding sentences as context. Towards this task, two main architectures have been applied, namely single-encoder (based on concatenation) and…