21 citations · 77 across the 26 of their papers we have counts for
15 papers · 1 filter
Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection
Atharva Kulkarni, Yuan Zhang, Joel Ruben Antony Moniz +5
Hallucinations pose a significant obstacle to the reliability and widespread adoption of language models, yet their accurate measurement remains a persistent challenge. While many…
SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages
Holy Lovenia, Rahmad Mahendra, Salsabil Maulana Akbar +58
Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1,300 indigenous languages and a population of 671 million people. However, prevailing…
ReALM: Reference Resolution As Language Modeling
Joel Ruben Antony Moniz, Soundarya Krishnan, Melis Ozyildirim +4
Reference resolution is an important problem, one that is essential to understand and successfully handle context of different kinds. This context includes both previous turns and…
SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking
Atharva Kulkarni, Bo-Hsiang Tseng, Joel Ruben Antony Moniz +3
In-context learning with Large Language Models (LLMs) has emerged as a promising avenue of research in Dialog State Tracking (DST). However, the best-performing in-context learning…
Can Large Language Models Understand Context?
Yilun Zhu, Joel Ruben Antony Moniz, Shruti Bhargava +6
Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. Howe…
MARRS: Multimodal Reference Resolution System
Halim Cagri Ates, Shruti Bhargava, Site Li +15
Successfully handling context is essential for any dialog understanding task. This context maybe be conversational (relying on previous user queries or system responses), visual (r…
STEER: Semantic Turn Extension-Expansion Recognition for Voice Assistants
Leon Liyang Zhang, Jiarui Lu, Joel Ruben Antony Moniz +5
In the context of a voice assistant system, steering refers to the phenomenon in which a user issues a follow-up command attempting to direct or clarify a previous turn. We propose…
Intelligent Assistant Language Understanding On Device
Cecilia Aas, Hisham Abdelsalam, Irina Belousova +20
It has recently become feasible to run personal digital assistants on phones and other personal devices. In this paper we describe a design for a natural language understanding sys…
5IDER: Unified Query Rewriting for Steering, Intent Carryover, Disfluencies, Entity Carryover and Repair
Jiarui Lu, Bo-Hsiang Tseng, Joel Ruben Antony Moniz +4
Providing voice assistants the ability to navigate multi-turn conversations is a challenging problem. Handling multi-turn interactions requires the system to understand various con…
On Efficiently Acquiring Annotations for Multilingual Models
Joel Ruben Antony Moniz, Barun Patra, Matthew R. Gormley
When tasked with supporting multiple languages for a given problem, two approaches have arisen: training a model for each language with the annotation budget divided equally among…
Using Pause Information for More Accurate Entity Recognition
Sahas Dendukuri, Pooja Chitkara, Joel Ruben Antony Moniz +3
Entity tags in human-machine dialog are integral to natural language understanding (NLU) tasks in conversational assistants. However, current systems struggle to accurately parse s…
DEXTER: Deep Encoding of External Knowledge for Named Entity Recognition in Virtual Assistants
Deepak Muralidharan, Joel Ruben Antony Moniz, Weicheng Zhang +6
Named entity recognition (NER) is usually developed and tested on text from well-written sources. However, in intelligent voice assistants, where NER is an important component, inp…
Noise Robust Named Entity Understanding for Voice Assistants
Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao +21
Named Entity Recognition (NER) and Entity Linking (EL) play an essential role in voice assistant interaction, but are challenging due to the special difficulties associated with sp…
Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces
Barun Patra, Joel Ruben Antony Moniz, Sarthak Garg +2
Recent work on bilingual lexicon induction (BLI) has frequently depended either on aligned bilingual lexicons or on distribution matching, often with an assumption about the isomet…
Nested LSTMs
Joel Ruben Antony Moniz, David Krueger
We propose Nested LSTMs (NLSTM), a novel RNN architecture with multiple levels of memory. Nested LSTMs add depth to LSTMs via nesting as opposed to stacking. The value of a memory…