Abstract

In this paper, we propose a method of reranking the outputs of Neural Machine Translation (NMT) systems. After the decoding process, we select a few last iteration outputs in the training process as the N-best list. After training a Neural Machine Translation (NMT) baseline system, it has been observed that these iteration outputs have an oracle score higher than baseline up to 1.01 BLEU points compared to the last iteration of the trained system.We come up with a ranking mechanism by solely focusing on the decoder’s ability to generate distinct tokens and without the usage of any language model or data. With this method, we achieved a translation improvement up to +0.16 BLEU points over baseline.We also evaluate our approach by applying the coverage penalty to the training process.In cases of moderate coverage penalty, the oracle scores are higher than the final iteration up to +0.99 BLEU points, and our algorithm gives an improvement up to +0.17 BLEU points.With excessive penalty, there is a decrease in translation quality compared to the baseline system. Still, an increase in oracle scores up to +1.30 is observed with the re-ranking algorithm giving an improvement up to +0.15 BLEU points is found in case of excessive penalty.The proposed re-ranking method is a generic one and can be extended to other language pairs as well.

Abstract

A large percentage of the world’s population speaks a language of the Indian subcontinent,comprising languages from both Indo-Aryan (e.g. Hindi, Punjabi, Gujarati, etc.) and Dravidian (e.g. Tamil, Telugu, Malayalam, etc.) families. A universal characteristic of Indian languages is their complex morphology, which, when combined with the general lack of sufficient quantities of high-quality parallel data, can make developing machine translation (MT) systems for these languages difficult. Neural Machine Translation (NMT) is a rapidly advancing MT paradigm and has shown promising results for many language pairs, especially in large training data scenarios. Since the condition of large parallel corpora is not met for Indian-English language pairs, we present our efforts towards building efficient NMT systems between Indian languages (specifically Indo-Aryan languages) and English via efficiently exploiting parallel data from the related languages. We propose a technique called Unified Transliteration and Subword Segmentation to leverage language similarity while exploiting parallel data from related language pairs. We also propose a Multilingual Transfer Learning technique to leverage parallel data from multiple related languages to assist translation for lowresource language pair of interest. Our experiments demonstrate an overall average improvement of 5 BLEU points over the standard Transformer-based NMT baselines.

Abstract

Negotiation is an important component of the interaction process among humans. With increasing automation, autonomous agents are expected to take over a lot of this interaction process. Much of automated negotiation literature focuses on agents having a static and known reservation value. In situations involving dynamic environments eg, an agent negotiating on behalf of a human regarding a meeting, agents can have a reservation value (RV) that is a function of time. This leads to a different set of challenges that may need additional reasoning about the concession behavior. In this paper, we build upon Negotiation algorithms such as ONAC (Optimal Non-Adaptive Concession) and Time-Dependent Techniques such as Boulware which work on settings where the reservation value of the agent is fixed and known. Although these algorithms can encode dynamic RV, their concession behavior and hence the …

Abstract

Automated negotiation between computational agents or between agents and humans has been a subject of active research with a focus on obtaining better quality solutions within reasonable time frames. The critical issue negotiators face during automated negotiation is that a negotiator may not always know the personality type of the opponent. Studies show that having information about the opponent improves the outcome of negotiation in general. However, unless there is prior knowledge, learning the opponent type in the limited amount of time or number of rounds in a negotiation is a difficult task. In this paper, we use a Partially Observable Markov Decision Process (POMDP) based modeling to perform better modeling of the opponent personality type. In particular, we focus on modeling the opponent into four different types to showcase that a better understanding of personality type can improve the outcome …

Abstract

In this paper, we present a multispeaker localization method using the time delay estimates obtained from the spectral features derived from the single frequency filter (SFF) representation. The mixture signals are transformed into SFF domain from which the temporal envelopes are extracted at each frequency. Subsequently, the spectral features such as mean and variance of temporal envelopes across frequencies are correlated for extracting the time delay estimates. Since these features emphasize the high SNR regions of the mixtures, correlation of the corresponding features across the channels leads to robust delay estimates in real acoustic environments. We study the efficacy of the developed approach by comparing its performance with the existing correlation based time delay estimation techniques. Both, a standard data set recorded in real-room acoustic environments and simulated data set are used for …

Abstract

n generation of emotional speech, there are deviations in the speech production features when compared to neutral (non-emotional) speech. The objective of this study is to capture the deviations in features related to the excitation component of speech and to develop a system for automatic recognition of emotions based on these deviations. The emotions considered in this study are anger, happiness, sadness and neutral state. The study shows that there are useful features in the deviations of the excitation features, which can be exploited to develop an emotion recognition system. The excitation features used in this study are the instantaneous fundamental frequency (), the strength of excitation, the energy of excitation and the ratio of the high-frequency to low-frequency band energy (). A hierarchical binary decision tree approach is used to develop an emotion recognition system with neutral speech …

Abstract

This paper presents a Bayesian multilingual topic model for learning language-independent document embeddings. Our model learns to represent the documents in the form of Gaussian distributions, thereby encoding the uncertainty in its covariance. We propagate the learned uncertainties through linear classifiers for zero-shot cross-lingual topic identification. Our experiments on 5 language Europarl and Reuters (MLDoc) corpora show that the proposed model outperforms multi-lingual word embedding and BiLSTM sentence encoder based systems with significant margins in the majority of the transfer directions. Moreover, our system trained under a single day on a single GPU with much lower amounts of data performs competitively as compared to the state-of-the-art universal BiLSTM sentence encoder trained on 93 languages. Our experimental analysis shows that the amount of parallel data improves the overall performance of embeddings. Nonetheless, exploiting the uncertainties is always beneficial.

Abstract

This paper presents the Question Answering (QA) system for a low resource language like ‘Telugu’ named ‘AVADHAN’. This work started with preparing a pre-tagged data set for Telugu Question Classification (QC). We also explained the ambiguities and complexities involved in the data set. AVADHAN exhibits the comparisons between Support Vector Machine (SVM), Logistic Regression (LR) and Multi-Layer Perceptron (MLP) classifiers for achieving the plausible answers. After performing various experiments the overall accuracies obtained, for both ‘exact match’ and ‘partial match’ based approaches, were for SVM (31.6%, 68.5%), LR (31%, 66.6%) and for MLP (30%, 67%) respectively

Abstract

Similar question retrieval is a challenge due to lexical gap between query and candidates in archive and is very different from traditional IR methods for duplicate detection, paraphrase identification and semantic equivalence. This tutorial covers recent deep learning techniques which overcome feature engineering issues with existing approaches based on translation models and latent topics. Hands-on proposal thus will introduce each concept from end user (e.g., questionanswer pairs) and technique (e.g., attention) perspectives, present state of the art methods and a walkthrough of programs executed on Jupyter notebook using real-world datasets demonstrating principles introduced

Abstract

The advent of social media has immensely proliferated the amount of opinions and arguments voiced on the internet. These virtual debates often present cases of aggression. While research has been focused largely on analyzing aggression and stance in isolation from each other, this work is the first attempt to gain an extensive and fine-grained understanding of patterns of aggression and figurative language use when voicing opinion. We present a Hindi-English code-mixed dataset of opinion on the politico-social issue of ‘2016 India banknote demonetisation‘ and annotate it across multiple dimensions such as aggression, hate speech, emotion arousal and figurative language usage (such as sarcasm/irony, metaphors/similes, puns/word-play)