Search Results for author:
Found 34 papers, 12 papers with code
ODIST: Open World Classification via Distributionally Shifted Instances
In this work, we address the open-world classification problem with a method called ODIST, open world classification via distributionally shifted instances.
FLAP: Flow-Adhering Planning with Constrained Decoding in LLMs
To study this, we propose the problem of faithful planning in TODs that needs to resolve user intents by following predefined flows and preserving API dependencies.
Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders
The triplet task gauges the model's understanding of two semantic concepts paramount in real-world conversational systems-- negation and implicature.
Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
Semi-supervised dialogue summarization (SSDS) leverages model-generated summaries to reduce reliance on human-labeled data and improve the performance of summarization models.
Abstractive Text Summarization
Natural Language Understanding
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Development of multimodal interactive systems is hindered by the lack of rich, multimodal (text, images) conversational data, which is needed in large quantities for LLMs.
Eliciting Better Multilingual Structured Reasoning from LLMs through Code
xSTREET exposes a gap in base LLM performance between English and non-English reasoning tasks.
TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization
We find that there are diverse errors and error distributions in model-generated summaries and that non-LLM based metrics can capture all error types better than LLM-based evaluators.
DeAL: Decoding-time Alignment for Large Language Models
Current work focuses on alignment at model training time, through techniques such as Reinforcement Learning with Human Feedback (RLHF).
Enhancing Abstractiveness of Summarization Models through Calibrated Distillation
Our experiments show that DisCal outperforms prior methods in abstractive summarization distillation, producing highly abstractive and informative summaries.
User Simulation with Large Language Models for Evaluating Task-Oriented Dialogue
One of the major impediments to the development of new task-oriented dialogue (TOD) systems is the need for human evaluation at multiple stages and iterations of the development process.
NatCS: Eliciting Natural Customer Support Dialogues
Existing task-oriented dialogue datasets, which were collected to benchmark dialogue systems mainly in written human-to-bot settings, are not representative of real customer support conversations and do not provide realistic benchmarks for systems that are applied to natural data.
Intent Induction from Conversations for Task-Oriented Dialogue Track at DSTC 11
With increasing demand for and adoption of virtual assistants, recent work has investigated ways to accelerate bot schema design through the automatic induction of intents or the induction of slots and dialogue states.
Conversation Style Transfer using Few-Shot Learning
Conventional text style transfer approaches focus on sentence-level style transfer without considering contextual information, and the style is described with attributes (e. g., formality).
Dialog2API: Task-Oriented Dialogue with API Description and Example Programs
The conversational model interacts with the environment by generating and executing programs triggering a set of pre-defined APIs.
Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systems
Pre-trained language models (PLM) have advanced the state-of-the-art across NLP applications, but lack domain-specific knowledge that does not naturally occur in pre-training data.
DFEE: Interactive DataFlow Execution and Evaluation Kit
DataFlow has been emerging as a new paradigm for building task-oriented chatbots due to its expressive semantic representations of the dialogue tasks.
Parameter and Data Efficient Continual Pre-training for Robustness to Dialectal Variance in Arabic
While prior research studies have tried to adapt these multilingual models for dialectal variants of Arabic, it still remains a challenging problem owing to the lack of sufficient monolingual dialectal data and parallel translation data of such dialectal variants.
Robustification of Multilingual Language Models to Real-world Noise in Crosslingual Zero-shot Settings with Robust Contrastive Pretraining
To benchmark the performance of pretrained multilingual language models, we construct noisy datasets covering five languages and four NLP tasks and observe a clear gap in the performance between clean and noisy data in the zero-shot cross-lingual setting.
Data Augmentation
Pretrained Multilingual Language Models
+1
Label Semantic Aware Pre-training for Few-shot Text Classification
Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction.
Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings
Recent studies have proposed different methods to improve multilingual word representations in contextualized settings including techniques that align between source and target embedding spaces.
Nearest Neighbour Few-Shot Learning for Cross-lingual Classification
Even though large pre-trained multilingual models (e. g. mBERT, XLM-R) have led to significant performance gains on a wide range of cross-lingual NLP tasks, success on many downstream tasks still relies on the availability of sufficient annotated data.
Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer
Multilingual pre-trained contextual embedding models (Devlin et al., 2019) have achieved impressive performance on zero-shot cross-lingual transfer tasks.
Knowledge-Driven Slot Constraints for Goal-Oriented Dialogue Systems
Practically, some combinations of slot values can be invalid according to external knowledge.
On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise
In this work, we investigate how robust IC/SL models are to noisy data.
End-to-End Slot Alignment and Recognition for Cross-Lingual NLU
We introduce MultiATIS++, a new multilingual NLU corpus that extends the Multilingual ATIS corpus to nine languages across four language families, and evaluate our method using the corpus.
Arabic-Segmentation Combination Strategies for Statistical Machine Translation
Next, we try a different strategy, where we combine the different segmentation methods rather than the different segmentation schemes.
A Holistic Approach to Bilingual Sentence Fragment Extraction from Comparable Corpora
Achieving accurate translation, especially in multiple domain documents with statistical machine translation systems, requires more and more bilingual texts and this need becomes more critical when training such systems for language pairs with scarce training data.
