Publications

Every day, tens of thousands of Amazon customers message Amazon’s selling partners inquiring about orders, products and services. Unfortunately, we have observed over time that buyers may send unsolicited and often times mal intended messages to sellers through the buyer-seller messaging (BSM) service. Although the BSM service gives the ability to sellers to report such messages, most of them do not make

Motivated by the many real-world applications of reinforcement learning (RL) that require safe-policy iterations, we consider the problem of off-policy evaluation (OPE) — the problem of evaluating a new policy using the historical data obtained by different behavior policies — under the model of nonstationary episodic Markov Decision Processes with a long horizon and large action space. Existing importance

Training dialog policies for speech-based virtual assistants requires a plethora of conversational data. The data collection phase is often expensive and time consuming due to human involvement. To address this issue, a common solution is to build user simulators for data generation. For the successful deployment of the trained policies into real world domains, it is vital that the user simulator mimics

Contextual word embeddings (e.g. GPT,BERT, ELMo, etc.) have demonstrated state-of-the-art performance on various NLP tasks. Recent work with the multilingual version of BERT has shown that the model performs very well in cross-lingual settings, even when only labeled English data is used to fine-tune the model. We improve upon multilingual BERT’s zero-resource cross-lingual performance via adversarial learning

Enabling cross-lingual NLP tasks by leveraging multilingual word embedding has recently attracted much attention. An important motivation is to support lower resourced languages, however, most efforts focus on demonstrating the effectiveness of the techniques using embeddings derived from similar languages toEnglish with large parallel content. In this study, we present a noise tolerant piecewise linear

Bayesian optimization (BO) is a model-based approach to minimize expensive black-boxes, and has been widely used to tune the hyperparameters of complex models such as deep neural networks. For many real-world black-boxes, however, the optimization is further subject to a priori unknown constraints. For example, model training may fail for certain configurations due to divergence or out of memory errors.

Short text classification is a fundamental problem in natural language processing, social network analysis, and e-commerce. Traditional approaches for classifying text do not generalize to short texts, due to the lack of structure that is prevalent in longer sentences and paragraphs. More recently, deep learning-based methods have been applied to this problem, with limited success. To overcome the limitations

The recent advances introduced by neural machine translation (NMT) are rapidly expanding the application fields of machine translation, as well as reshaping the quality level to be targeted. In particular, if translations have to fit some given layout, quality should not only be measured in terms of adequacy and fluency, but also length. Exemplary cases are the translation of document files, subtitles, and

Neural machine translation models have shown to achieve high quality when trained and fed with well structured and punctuated input texts. Unfortunately, the latter condition is not met in spoken language translation, where the input is generated by an automatic speech recognition (ASR) system. In this paper, we study how to adapt a strong NMT system to make it robust to typical ASR errors. As in our application

Robustness to capitalization errors is a highly desirable characteristic of named entity recognizers, yet we find standard models for the task are surprisingly brittle to such noise. Existing methods to improve robustness to the noise completely discard given orthographic information, which significantly degrades their performance on well-formed text. We propose a simple alternative approach based on data

In this paper, we propose a weak supervision framework for neural ranking tasks based on the data programming paradigm (Ratner et al., 2016), which enables us to leverage multiple weak supervision signals from different sources. Empirically, we consider two sources of weak supervision signals, unsupervised ranking functions and semantic feature similarities. We train a BERT-based passageranking model (which

Offline handwriting recognition with deep neural networks is usually limited to words or lines due to large computational costs. In this paper, a less computationally expensive full page offline handwritten text recognition framework is introduced. This framework includes a pipeline that locates handwritten text with an object detection neural network and recognises the text within the detected regions

Relation Extraction is the task of identifying entity mention spans in raw text and then identifying relations between pairs of the entity mentions. Recent approaches for this spanlevel task have been token-level models which have inherent limitations. They cannot easily define and implement span-level features, cannot model overlapping entity mentions and have cascading errors due to the use of sequential

On-policy reinforcement learning (RL) algorithms have high sample complexity while offpolicy algorithms are difficult to tune. Merging the two holds the promise to develop efficient algorithms that generalize across diverse environments. It is however challenging in practice to find suitable hyper-parameters that govern this trade off. This paper develops a simple algorithm named P3O that interleaves offpolicy

In this work, we describe limitations of the free-field propagation model for designing broadband beamformers for microphone arrays on a rigid surface. Towards this goal, we describe a general framework for quantifying the microphone array performance in a general wave-field by directly solving the acoustic wave equation. The model utilizes Finite-Element-Method (FEM) for evaluating the response of the