Related papers: Frequency Effects on Syntactic Rule Learning in Tr…
Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We assess the ability of modern neural language models to reproduce…
Targeted syntactic evaluations have demonstrated the ability of language models to perform subject-verb agreement given difficult contexts. To elucidate the mechanisms by which the models accomplish this behavior, this study applies causal…
In the current landscape of language model research, larger models, larger datasets and more compute seems to be the only way to advance towards intelligence. While there have been extensive studies of scaling laws and models' scaling…
Pretraining sentence encoders with language modeling and related unsupervised tasks has recently been shown to be very effective for language understanding tasks. By supplementing language model-style pretraining with further training on…
In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems. We use a wide set…
Tremendous amounts of multimedia associated with speech information are driving an urgent need to develop efficient and effective automatic summarization methods. To this end, we have seen rapid progress in applying supervised deep neural…
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,…
Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks. The Transformer, for instance, is an illustrative example that generates abstract representations of tokens inputted to an encoder…
Pre-trained model representations have demonstrated state-of-the-art performance in speech recognition, natural language processing, and other applications. Speech models, such as Bidirectional Encoder Representations from Transformers…
Since the popularization of the Transformer as a general-purpose feature encoder for NLP, many studies have attempted to decode linguistic structure from its novel multi-head attention mechanism. However, much of such work focused almost…
BERT is a popular language model whose main pre-training task is to fill in the blank, i.e., predicting a word that was masked out of a sentence, based on the remaining words. In some applications, however, having an additional context can…
Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…
A line of work on Transformer-based language models such as BERT has attempted to use syntactic inductive bias to enhance the pretraining process, on the theory that building syntactic structure into the training process should reduce the…
Several pre-training objectives, such as masked language modeling (MLM), have been proposed to pre-train language models (e.g. BERT) with the aim of learning better language representations. However, to the best of our knowledge, no…
Language models have become nearly ubiquitous in natural language processing applications achieving state-of-the-art results in many tasks including prosody. As the model design does not define predetermined linguistic targets during…
In this paper, we study the response of large models from the BERT family to incoherent inputs that should confuse any model that claims to understand natural language. We define simple heuristics to construct such examples. Our experiments…
Deep architectures such as Transformers are sometimes criticized for having uninterpretable "black-box" representations. We use causal intervention analysis to show that, in fact, some linguistic features are represented in a linear,…
While there has been much recent work studying how linguistic information is encoded in pre-trained sentence representations, comparatively little is understood about how these models change when adapted to solve downstream tasks. Using a…
Several studies have been carried out on revealing linguistic features captured by BERT. This is usually achieved by training a diagnostic classifier on the representations obtained from different layers of BERT. The subsequent…
Detecting the user's intent and finding the corresponding slots among the utterance's words are important tasks in natural language understanding. Their interconnected nature makes their joint modeling a standard part of training such…