Related papers: Distantly-Supervised Evidence Retrieval Enables Qu…

With an exponential explosive growth of various digital text information, it is challenging to efficiently obtain specific knowledge from massive unstructured text information. As one basic task for natural language processing (NLP),…

We introduce ART, a new corpus-level autoencoding approach for training dense retrieval models that does not require any labeled training data. Dense retrieval is a central challenge for open-domain tasks, such as Open QA, where…

Although evidence integration to the boundary model has successfully explained a wide range of behavioral and neural data in decision making under uncertainty, how animals learn and optimize the boundary remains unresolved. Here, we propose…

Imitation learning seeks to circumvent the difficulty in designing proper reward functions for training agents by utilizing expert behavior. With environments modeled as Markov Decision Processes (MDP), most of the existing imitation…

This paper studies the bias problem of multi-hop question answering models, of answering correctly without correct reasoning. One way to robustify these models is by supervising to not only answer right, but also with right reasoning…

Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applications. To tackle this issue,…

To alleviate human efforts from obtaining large-scale annotations, Semi-Supervised Relation Extraction methods aim to leverage unlabeled data in addition to learning from limited samples. Existing self-training methods suffer from the…

Generalising dialogue state tracking (DST) to new data is especially challenging due to the strong reliance on abundant and fine-grained supervision during training. Sample sparsity, distributional shift and the occurrence of new concepts…

Self-supervised learning, which learns by constructing artificial labels given only the input signals, has recently gained considerable attention for learning representations with unlabeled datasets, i.e., learning without any…

While deep learning succeeds in a wide range of tasks, it highly depends on the massive collection of annotated data which is expensive and time-consuming. To lower the cost of data annotation, active learning has been proposed to…

Imitating musical instruments with the human voice is an efficient way of communicating ideas between music producers, from sketching melody lines to clarifying desired sonorities. For this reason, there is an increasing interest in…

Knowledge-based question answering relies on the availability of facts, the majority of which cannot be found in structured sources (e.g. Wikipedia info-boxes, Wikidata). One of the major components of extracting facts from unstructured…

Complex deep learning models now achieve state of the art performance for many document retrieval tasks. The best models process the query or claim jointly with the document. However for fast scalable search it is desirable to have document…

Multi-hop question answering (MHQA) involves reasoning across multiple documents to answer complex questions. Dense retrievers typically outperform sparse methods like BM25 by leveraging semantic embeddings; however, they require labeled…

This paper proposes a novel training scheme for fast matching models in Search Ads, which is motivated by the real challenges in model training. The first challenge stems from the pursuit of high throughput, which prohibits the deployment…

The recent success of deep neural networks is powered in part by large-scale well-labeled training data. However, it is a daunting task to laboriously annotate an ImageNet-like dateset. On the contrary, it is fairly convenient, fast, and…

When a deep learning model is deployed in the wild, it can encounter test data drawn from distributions different from the training data distribution and suffer drop in performance. For safe deployment, it is essential to estimate the…

This paper is on active learning where the goal is to reduce the data annotation burden by interacting with a (human) oracle during training. Standard active learning methods ask the oracle to annotate data samples. Instead, we take a…

Most existing approaches to disfluency detection heavily rely on human-annotated corpora, which is expensive to obtain in practice. There have been several proposals to alleviate this issue with, for instance, self-supervised learning…

Active learning aims to develop label-efficient algorithms by querying the most informative samples to be labeled by an oracle. The design of efficient training methods that require fewer labels is an important research direction that…