Related papers: Improved Latent Tree Induction with Distant Superv…
State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks. Weak supervision in the form of domain-specific rules has been shown to be useful in such…
We propose a novel, semi-supervised approach towards domain taxonomy induction from an input vocabulary of seed terms. Unlike all previous approaches, which typically extract direct hypernym edges for terms, our approach utilizes a novel…
Learning sentence embeddings often requires a large amount of labeled data. However, for most tasks and domains, labeled data is seldom available and creating it is expensive. In this work, we present a new state-of-the-art unsupervised…
Temporal sentence grounding aims to detect the event timestamps described by the natural language query from given untrimmed videos. The existing fully-supervised setting achieves great performance but requires expensive annotation costs;…
Recent trends in self-supervised representation learning have focused on removing inductive biases from training pipelines. However, inductive biases can be useful in settings when limited data are available or provide additional insight…
Semantic role labeling (SRL) is a fundamental yet challenging task in the NLP community. Recent works of SRL mainly fall into two lines: 1) BIO-based; 2) span-based. Despite ubiquity, they share some intrinsic drawbacks of not considering…
The current trend in automatic speech recognition is to leverage large amounts of labeled data to train supervised neural network models. Unfortunately, obtaining data for a wide range of domains to train robust models can be costly.…
The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. Nevertheless, the intrinsic geometric constraint forces it to focus on the regions with close spatial distance,…
Medical language-guided segmentation, integrating textual clinical reports as auxiliary guidance to enhance image segmentation, has demonstrated significant improvements over unimodal approaches. However, its inherent reliance on paired…
In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach…
Pre-training Transformer from large-scale raw texts and fine-tuning on the desired task have achieved state-of-the-art results on diverse NLP tasks. However, it is unclear what the learned attention captures. The attention computed by…
Unsupervised constituency parsers organize phrases within a sentence into a tree-shaped syntactic constituent structure that reflects the organization of sentence semantics. However, the traditional objective of maximizing sentence…
Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities. However, effective aggregation of relevant…
The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions. Since the target domain usually lacks labeled data, and domain shifts exist at…
We describe a simple method for unsupervised domain adaptation, whereby the discrepancy between the source and target distributions is reduced by swapping the low-frequency spectrum of one with the other. We illustrate the method in…
Unsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic segmentation in particular, it helps deploy on real "target domain" data models that are…
Although self-attention networks (SANs) have advanced the state-of-the-art on various NLP tasks, one criticism of SANs is their ability of encoding positions of input words (Shaw et al., 2018). In this work, we propose to augment SANs with…
Most previous work on grammar induction focuses on learning phrasal or dependency structure purely from text. However, because the signal provided by text alone is limited, recently introduced visually grounded syntax models make use of…
Despite achieving promising results in a breadth of medical image segmentation tasks, deep neural networks require large training datasets with pixel-wise annotations. Obtaining these curated datasets is a cumbersome process which limits…
Parsing sentences into syntax trees can benefit downstream applications in NLP. Transition-based parsers build trees by executing actions in a state transition system. They are computationally efficient, and can leverage machine learning to…