Gayatri Bhat

Hamna, Gayatri Bhat, Sourabrata Mukherjee et al.

Large Language Models (LLMs) are typically evaluated through general or domain-specific benchmarks testing capabilities that often lack grounding in the lived realities of end users. Critical domains such as healthcare require evaluations that extend beyond artificial or simulated tasks to reflect the everyday needs, cultural practices, and nuanced contexts of communities. We propose Samiksha, a community-driven evaluation pipeline co-created with civil-society organizations (CSOs) and community members. Our approach enables scalable, automated benchmarking through a culturally aware, community-driven pipeline in which community feedback informs what to evaluate, how the benchmark is built, and how outputs are scored. We demonstrate this approach in the health domain in India. Our analysis highlights how current multilingual LLMs address nuanced community health queries, while also offering a scalable pathway for contextually grounded and inclusive LLM evaluation.

Gayatri Bhat, Avneesh Saluja, Melody Dye et al.

While natural language understanding of long-form documents is still an open challenge, such documents often contain structural information that can inform the design of models for encoding them. Movie scripts are an example of such richly structured text - scripts are segmented into scenes, which are further decomposed into dialogue and descriptive components. In this work, we propose a neural architecture for encoding this structure, which performs robustly on a pair of multi-label tag classification datasets, without the need for handcrafted features. We add a layer of insight by augmenting an unsupervised "interpretability" module to the encoder, allowing for the extraction and visualization of narrative trajectories. Though this work specifically tackles screenplays, we discuss how the underlying approach can be generalized to a range of structured documents.

Aditi Chaudhary, Elizabeth Salesky, Gayatri Bhat et al.

This paper presents the submission by the CMU-01 team to the SIGMORPHON 2019 task 2 of Morphological Analysis and Lemmatization in Context. This task requires us to produce the lemma and morpho-syntactic description of each token in a sequence, for 107 treebanks. We approach this task with a hierarchical neural conditional random field (CRF) model which predicts each coarse-grained feature (eg. POS, Case, etc.) independently. However, most treebanks are under-resourced, thus making it challenging to train deep neural models for them. Hence, we propose a multi-lingual transfer training regime where we transfer from multiple related languages that share similar typology.

Gayatri Bhat, Monojit Choudhury, Kalika Bali

We make one of the first attempts to build working models for intra-sentential code-switching based on the Equivalence-Constraint (Poplack 1980) and Matrix-Language (Myers-Scotton 1993) theories. We conduct a detailed theoretical analysis, and a small-scale empirical study of the two models for Hindi-English CS. Our analyses show that the models are neither sound nor complete. Taking insights from the errors made by the models, we propose a new model that combines features of both the theories.