This paper investigates part-of-speech tagging, an important task in Natural Language Processing (NLP) for the Nagamese language. The Nagamese language, a.k.a. Naga Pidgin, is an Assamese-lexified Creole language developed primarily as a means of communication in trade between the Nagas and people from Assam in northeast India. A substantial amount of work in part-of-speech-tagging has been done for resource-rich languages like English, Hindi, etc. However, no work has been done in the Nagamese language. To the best of our knowledge, this is the first attempt at part-of-speech tagging for the Nagamese Language. The aim of this work is to identify the part-of-speech for a given sentence in the Nagamese language. An annotated corpus of 16,112 tokens is created and applied machine learning technique known as Conditional Random Fields (CRF). Using CRF, an overall tagging accuracy of 85.70%; precision, recall of 86%, and f1-score of 85% is achieved. Keywords. Nagamese, NLP, part-of-speech, machine learning, CRF.

This article presents a curated resource and evaluation suite for punctuation-aware treebank binarization. Standard binarization pipelines drop punctuation before head selection, which alters constituent shape and harms head-child identification. We release (1) a reproducible pipeline that preserves punctuation as sibling nodes prior to binarization, (2) derived artifacts and metadata (intermediate @X markers, reversibility signatures, alignment indices), and (3) an accompanying evaluation suite covering head-child prediction, round-trip reversibility, and structural compatibility with derivational resources (CCGbank). On the Penn Treebank, punctuation-aware preprocessing improves head prediction accuracy from 73.66\% (Collins rules) and 86.66\% (MLP) to 91.85\% with the same classifier, and achieves competitive alignment against CCGbank derivations. All code, configuration files, and documentation are released to enable replication and extension to other corpora.

Establishing shared goals is a fundamental step in human-AI communication. However, ambiguities can lead to outputs that seem correct but fail to reflect the speaker's intent. In this paper, we explore this issue with a focus on the data visualization domain, where ambiguities in natural language impact the generation of code that visualizes data. The availability of multiple views on the contextual (e.g., the intended plot and the code rendering the plot) allows for a unique and comprehensive analysis of diverse ambiguity types. We develop a taxonomy of types of ambiguity that arise in this task and propose metrics to quantify them. Using Matplotlib problems from the DS-1000 dataset, we demonstrate that our ambiguity metrics better correlate with human annotations than uncertainty baselines. Our work also explores how multi-turn dialogue can reduce ambiguity, therefore, improve code accuracy by better matching user goals. We evaluate three pragmatic models to inform our dialogue strategies: Gricean Cooperativity, Discourse Representation Theory, and Questions under Discussion. A simulated user study reveals how pragmatic dialogues reduce ambiguity and enhance code accuracy, highlighting the value of multi-turn exchanges in code generation.

Model Parsing defines the task of predicting hyperparameters of the generative model (GM), given a GM-generated image as the input.

Work partially completed while at Microsoft Research.

In each case, the ambiguity persists even when the database context is provided.