Test of Time Awards

Presidential Address

A key contribution to being a successful researcher in natural language processing, as in any area, is having a clear overarching vision of what your body of research is trying to accomplish. Using my own 40-year career as an example, I will attempt to provide general advice on formulating and pursuing a coherent research vision. In particular, I will focus on formulating a unique, personal objective that exploits your specific talents, knowledge, and passions, and that is distinct from the current popular trends in the field. I will also focus on formulating a vision that bridges existing fields of study to produce an overarching agenda that unifies previously disparate ideas.

The Vision Thing: Finding and Pursuing your Research Passion

One of the frequent points in the mainstream narrative about large language models is that they have “emergent properties” (sometimes even dangerous enough to be considered existential risk to mankind). However, there is much disagreement about even the very definition of such properties. If they are understood as a kind of generalization beyond training data - as something that a model does without being explicitly trained for it - I argue that we have not in fact established the existence of any such properties, and at the moment we do not even have the methodology for doing so.

A sanity check on emergent properties

Transliteration is very important in the Indian
language context due to the usage of multi-
ple scripts and the widespread use of roman-
ized inputs. However, few training and evalu-
ation sets are publicly available. We introduce
Aksharantar1, the largest publicly available
transliteration dataset for Indian languages cre-
ated by mining from monolingual and paral-
lel corpora, as well as collecting data from hu-
man annotators. The dataset contains 26 mil-
lion transliteration pairs for 21 Indic lan-
guages from 3 language families using 12
scripts. Aksharantar is 21 times larger than ex-
isting datasets and is the first publicly available
dataset for 7 languages and 1 language fam-
ily. We also introduce the Aksharantar testset
comprising 103k word pairs spanning 19 lan-
guages that enables a fine-grained analysis of
transliteration models on native origin words,
foreign words, frequent words, and rare words.
Using the training set, we trained IndicXlit,
a multilingual transliteration model that im-
proves accuracy by 15% on the Dakshina test
set, and establishes strong baselines on the Ak-
sharantar testset introduced in this work. The
models, mining scripts, transliteration guide-
lines, and datasets are available at https://
github.com/AI4Bharat/IndicXlit under
open-source licenses.

Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users

The presentation titled "CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text" introduces a novel framework designed to enhance the processing and understanding of procedural text. CLMSM stands out by its unique approach of utilizing metadata from procedures, integrating a Contrastive Learning strategy for global context comprehension, and employing Masked Step Modeling to capture local context nuances. This framework addresses the inherent challenge in procedural text processing – the need for a temporal understanding and tracking of entities across steps, a critical aspect that conventional pre-training methods like Masked Language Modeling (MLM) often overlook.

In this presentation, we demonstrate how CLMSM significantly outperforms various baseline models in entity tracking tasks, underscoring the importance of in-domain pre-training for accurately learning temporal and entity-based information in procedures. The results are particularly notable in scenarios requiring the tracking of entities with implicit locations, highlighting CLMSM’s advanced knowledge retention capabilities. Additionally, we present insights into CLMSM's adaptability to out-of-domain tasks, further establishing its versatility. This framework not only sets a new standard in procedural text understanding but also opens avenues for future research, particularly in extending its applicability to other domains with procedural text, potentially unveiling new challenges and opportunities.

CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text

Inverse Text Normalization (ITN) involves rewriting the verbalised form of text from spoken transcripts to its corresponding written form. The task inherently expects challenges in identifying ITN entries due to spelling variations in words arising out of dialects, transcription errors etc. Additionally, in Tamil, word boundaries between adjacent words in a sentence often get obscured due to Punarchi, i.e. phonetic transformation of these boundaries. Being morphologically rich, the words in Tamil show a high degree of agglutination due to inflection and clitics. The combination of such factors leads to a high degree of surfaceform variations, making scalability with pure rule-based approaches difficult. Instead, we experiment with fine-tuning three pre-trained neural LMs, consisting of a seq2seq model (s2s), a non-autoregressive text editor (NAR) and a sequence tagger + rules combination (tagger). While the tagger approach works best in a fully-supervised setting, s2s performs the best (98.05 F-Score) when augmented with additional data, via bootstrapping and data augmentation (DA&B). S2S reports a cumulative percentage improvement of 20.1 %, and statistically significant gains for all our models with DA&B. Compared to a fully supervised setup, bootstrapping alone reports a percentage improvement as high as 14.12 %, even with a small seed set of 324 ITN entries.

Scaling Neural ITN for Numbers and Temporal Expressions in Tamil: Findings for an Agglutinative Low-resource Language | VIDEO

Large Language Models (LLMs) have made significant progress in utilizing tools, but their ability is limited by API availability and the instability of implicit reasoning, particularly when both planning and execution are involved. To overcome these limitations, we propose CREATOR, a novel framework that enables LLMs to create their own tools using documentation and code realization. CREATOR disentangles abstract tool creation and concrete decision execution, resulting in improved performance. We evaluate CREATOR on MATH and TabMWP benchmarks, respectively consisting of challenging math competition problems and diverse tabular contents. Remarkably, CREATOR outperforms existing chain-of-thought, program-of-thought, and tool-using baselines. Additionally, we introduce the Creation Challenge dataset, featuring 2K diverse questions, to emphasize the necessity and benefits of LLMs' tool creation ability. Further research demonstrates that leveraging LLMs as tool creators facilitates knowledge transfer, and LLMs exhibit varying levels of tool creation abilities, enabling them to adapt to diverse situations. The tool creation ability revolutionizes the LLM's problem-solving paradigm, driving us closer to the next frontier of artificial intelligence.

CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models

Many real-world tasks involve a mixed-initiative setup, wherein humans and AI systems collaboratively perform a task. While significant work has been conducted towards enabling humans to specify, through language, exactly how an agent should complete a task (i.e., low-level specification), prior work lacks on interpreting the high-level strategic intent of the human commanders. Parsing strategic intent from language will allow autonomous systems to independently operate according to the user's plan without frequent guidance or instruction. In this paper, we build a computational interface capable of translating unstructured language strategies into actionable intent in the form of goals and constraints. Leveraging a game environment, we collect a dataset of over 1000 examples, mapping language strategies to the corresponding goals and constraints, and show that our model, trained on this dataset, significantly outperforms human interpreters in inferring strategic intent (i.e., goals and constraints) from language (p < 0.05). Furthermore, we show that our model (125M parameters) significantly outperforms ChatGPT for this task (p < 0.05) in a low-data setting.

A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting | VIDEO

Emotion arcs capture how an individual (or a population) feels over time. They are widely used in industry and research; however, there is little work on evaluating the automatically generated arcs. This is because of the difficulty of establishing the true (gold) emotion arc. Our work, for the first time, systematically and quantitatively evaluates automatically generated emotion arcs. We also compare two common ways of generating emotion arcs: Machine-Learning (ML) models and Lexicon-Only (LexO) methods. By running experiments on 18 diverse datasets in 9 languages, we show that despite being markedly poor at instance level emotion classification, LexO methods are highly accurate at generating emotion arcs when aggregating information from hundreds of instances. We also show, through experiments on six indigenous African languages, as well as Arabic, and Spanish, that automatic translations of English emotion lexicons can be used to generate high-quality emotion arcs in less-resource languages. This opens up avenues for work on emotions in languages from around the world; which is crucial for commerce, public policy, and health research in service of speakers often left behind. Code and resources: https://github.com/dteodore/EmotionArcs

Evaluating Emotion Arcs Across Languages: Bridging the Global Divide in Sentiment Analysis

Large language models (LLMs) have shown increasing capacity at planning and executing a high-level goal in a live computer environment (e.g. MiniWoB++). To perform a task, recent works often require a model to learn from trace examples of the task via either supervised learning or few/many-shot prompting. Without these trace examples, it remains a challenge how an agent can autonomously learn and improve its control on a computer, which limits the ability of an agent to perform a new task. We approach this problem with a zero-shot agent that requires no given expert traces. Our agent plans for executable actions on a partially observed environment, and iteratively progresses a task by identifying and learning from its mistakes via self-reflection and structured thought management. On the easy tasks of MiniWoB++, we show that our zero-shot agent often outperforms recent SoTAs, with more efficient reasoning. For tasks with more complexity, our reflective agent performs on par with prior best models, even though previous works had the advantages of accessing expert traces or additional screen information.

A Zero-Shot Language Agent for Computer Control with Structured Reflection

Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification task, where the utterances are classified into predefined categories or as a clustering task when new and previously unknown intent categories need to be discovered from these utterances. Further, the intent classification may be modeled in a multiclass (MC) or multilabel (ML) setup. While typically these tasks are modeled as separate tasks, we propose INTENDD a unified approach leveraging a shared utterance encoding backbone. INTENDD uses an entirely unsupervised contrastive learning strategy for representation learning, where pseudo labels for the unlabeled utterances are generated based on their lexical features. Additionally, we introduce a two-step post-processing setup for the classification tasks using modified adsorption. Here, first, the residuals in the training data are propagated followed by smoothing the labels both modeled in a transductive setting. Through extensive evaluations on various benchmark datasets, we find that our approach consistently outperforms competitive baselines across all three tasks. On average, INTENDD reports percentage improvements of 2.32 %, 1.26 %, and 1.52 % in their respective metrics for few-shot MC, few-shot ML, and the intent discovery tasks respectively.

Underline digital video library

Test of Time Awards

Presidential Address

The Vision Thing: Finding and Pursuing your Research Passion

A sanity check on emergent properties

Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users

CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text

Scaling Neural ITN for Numbers and Temporal Expressions in Tamil: Findings for an Agglutinative Low-resource Language | VIDEO

CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models

A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting | VIDEO

Evaluating Emotion Arcs Across Languages: Bridging the Global Divide in Sentiment Analysis

A Zero-Shot Language Agent for Computer Control with Structured Reflection

IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES