In the realm of parameter-efficient fine-tuning (PEFT) methods, while options like LoRA are available, there is a persistent demand in the industry for a PEFT approach that excels in both efficiency and performance within the context of single-backbone multi-tenant applications. This paper introduces a new and straightforward PEFT technique, termed Prompt Aware Representation Adjustment (PARA). The core of our proposal is to integrate a lightweight vector generator within each Transformer layer. This generator produces vectors that are responsive to input prompts, thereby adjusting the hidden representations accordingly. Our extensive experimentation across diverse tasks has yielded promising results. Firstly, the PARA method has been shown to surpass current PEFT benchmarks in terms of performance, despite having a similar number of adjustable parameters. Secondly, it has proven to be more efficient than LoRA in the single-backbone multi-tenant scenario, highlighting its significant potential for industrial adoption.

Despite exciting progress in causal language models, the expressiveness of their representations is largely limited due to poor discrimination ability. To remedy this issue, we present CONTRACLM, a novel contrastive learning framework at both the token-level and the sequence-level. We assess CONTRACLM on a variety of downstream tasks. We show that CONTRACLM enhances the discrimination of representations and bridges the gap with encoder-only models, which makes causal language models better suited for tasks beyond language generation. Specifically, we attain 44% relative improvement on the Semantic Textual Similarity tasks and 34% on Code-to-Code Search tasks. Furthermore, by improving the expressiveness of representations, CONTRACLM also boosts the source code generation capability with 9% relative improvement on execution accuracy on the HumanEval benchmark.

Many machine learning-based low-code or no-code applications involve generating code that interacts with structured knowledge. For example, one of the most studied tasks in this area is generating SQL code from a natural language statement. Prior work shows that incorporating context information from the database schema, such as table and column names, is beneficial to model performance on this task. In this work we present a large pretraining dataset and strategy for learning representations of text, tables, and SQL code that leverages the entire context of the problem. Specifically, we build on existing encoder-decoder architecture by introducing a multitask pretraining framework that complements the unique attributes of our diverse pretraining data. Our work represents the first study on large-scale pretraining of encoder-decoder models for interacting with structured knowledge, and offers a new state-of-the-art foundation model in text-to-SQL generation. We validate our approach with experiments on two SQL tasks, showing improvement over existing methods, including a 1.7 and 2.2 percentage point improvement over prior state-of-the-arts on Spider and CoSQL.

Large-scale code generation models such as Copilot and CodeT5 have achieved impressive performance. However, libraries are upgraded or deprecated very frequently and re-training large-scale language models is computationally expensive. Therefore, Continual Learning (CL) is an important aspect that remains under-explored in the code domain. In this paper, we introduce a benchmark called CodeTask-CL that covers a wide range of tasks, including code generation, translation, summarization, and refinement, with different input and output programming languages. Next, on our CodeTask-CL benchmark, we compare popular CL techniques from NLP and Vision domains. We find that effective methods like Prompt Pooling (PP) suffer from catastrophic forgetting due to the unstable training of the prompt selection mechanism caused by stark distribution shifts in coding tasks. We address this issue with our proposed method, Prompt Pooling with Teacher Forcing (PP-TF), that stabilizes training by enforcing constraints on the prompt selection mechanism and leads to a 21.54% improvement over Prompt Pooling. Along with the benchmark, we establish a training pipeline that can be used for CL on code models, which we believe can motivate further development of CL methods for code models.

Recently, dynamic early exiting has attracted much attention since it can accelerate the inference speed of pre-trained models (PTMs). However, previous work on early exiting has neglected the intermediate exits’ architectural designs. In this work, we propose a novel framework, Learned Exits and COmparison-based early exiting (LECO) to improve PTMs’ early exiting performances. First, to fully uncover the potentials of multi-exit BERT, we design a novel search space for intermediate exits and employ the idea of differentiable neural architecture search (DNAS) to design proper exit architectures for different intermediate layers automatically. Second, we propose a simple-yet-effective comparison-based early exiting mechanism (COBEE), which can help PTMs achieve better performance and speedup tradeoffs. Extensive experiments show that our LECO achieves the SOTA performances for multi-exit BERT training and dynamic early exiting.

Recently, the recognition of flat, nested, and discontinuous entities by a unified generative model framework has received increasing attention both in the research field and industry. However, the current generative NER methods force the entities to be generated in a predefined order, suffering from error propagation and inefficient decoding. In this work, we propose a unified non-autoregressive generation (NAG) framework for general NER tasks, referred to as NAG-NER. First, we propose to generate entities as a set instead of a sequence, avoiding error propagation. Second, we propose incorporating NAG in NER tasks for efficient decoding by treating each entity as a target sequence. Third, to enhance the generation performances of the NAG decoder, we employ the NAG encoder to detect potential entity mentions. Extensive experiments show that our NAG-NER model outperforms the state-of-the-art generative NER models on three benchmark NER datasets of different types and two of our proprietary NER tasks.\footnote{Code will be publicly available to the research community upon acceptance.}

Recently, a series of works have looked into further improving the adapter-based tuning by manually designing better adapter architectures. Understandably, these manually designed solutions are sub-optimal. In this work, we propose the Learned Adapter framework to automatically learn the optimal adapter architectures for better task adaptation of pre-trained models (PTMs). First, we construct a unified search space for adapter architecture designs. In terms of the optimization method on the search space, we propose a simple-yet-effective method, GDNAS for better architecture optimization. Extensive experiments show that our Learned Adapter framework can outperform the previous parameter-efficient tuning (PETuning) baselines while tuning comparable or fewer parameters. Moreover: (a) the learned adapter architectures are explainable and transferable across tasks. (b) We demonstrate that our architecture search space design is valid.

Prompt tuning prepends a soft prompt to the input embeddings or hidden states and only optimizes the prompt to adapt pretrained models (PTMs) to downstream tasks. The previous work manually selects prompt layers which are far from optimal and failed to exploit the potential of prompt tuning. In this work, we propose a novel framework, Selective Prompt Tuning (SPT), that learns to select the proper prompt layers by inserting a prompt controlled by a learnable probabilistic gate at each intermediate layer. We further propose a novel bi-level optimization framework, SPT-DARTS, that can better optimize the learnable gates and improve the final prompt tuning performances of the learned prompt layer settings. We conduct extensive experiments with ten benchmark datasets under the full-data and few-shot scenarios. The results demonstrate that our SPT framework can perform better than the previous state-of-the-art PETuning baselines with comparable or fewer tunable parameters.

Large-scale pre-trained sequence-to-sequence models like BART and T5 achieve state-of-the-art performance on many generative NLP tasks. However, such models pose a great challenge in resource-constrained scenarios owing to their large memory requirements and high latency. To alleviate this issue, we propose to jointly distill and quantize the model, where knowledge is transferred from the full-precision teacher model to the quantized and distilled low-precision student model. Empirical analyses show that, despite the challenging nature of generative tasks, we were able to achieve a 16.5x model footprint compression ratio with little performance drop relative to the full-precision counterparts on multiple summarization and QA datasets. We further pushed the limit of compression ratio to 27.7x and presented the performance-efficiency trade-off for generative tasks using pre-trained models. To the best of our knowledge, this is the first work aiming to effectively distill and quantize sequence-to-sequence pre-trained models for language generation tasks.

Modern conversational AI systems support natural language understanding for a wide variety of capabilities. While a majority of these tasks can be accomplished using a simple and flat representation of intents and slots, more sophisticated capabilities require complex hierarchical representations supported by semantic parsing. State-of-the-art semantic parsers are trained using supervised learning with data labeled according to a hierarchical schema which might be costly to obtain or not readily available for a new domain. In this work, we explore the possibility of generating synthetic data for neural semantic parsing using a pretrained denoising sequence-to-sequence model (i.e., BART). Specifically, we first extract masked templates from the existing labeled utterances, and then fine-tune BART to generate synthetic utterances conditioning on the extracted templates. Finally, we use an auxiliary parser (AP) to filter the generated utterances. The AP guarantees the quality of the generated data. We show the potential of our approach when evaluating on the Facebook TOP dataset for navigation domain.

Many approaches to extract multiple relations from a paragraph require multiple passes over the paragraph. In practice, multiple passes are computationally expensive and this makes difficult to scale to longer paragraphs and larger text corpora. In this work, we focus on the task of multiple relation extractions by encoding the paragraph only once. We build our solution upon the pre-trained self-attentive models (Transformer), where we first add a structured prediction layer to handle extraction between multiple entity pairs, then enhance the paragraph embedding to capture multiple relational information associated with each entity with entity-aware attention. We show that our approach is not only scalable but can also perform state-of-the-art on the standard benchmark ACE 2005.

Out-of-domain (OOD) detection for low-resource text classification is a realistic but understudied task. The goal is to detect the OOD cases with limited in-domain (ID) training data, since in machine learning applications we observe that training data is often insufficient. In this work, we propose an OOD-resistant Prototypical Network to tackle this zero-shot OOD detection and few-shot ID classification task. Evaluations on real-world datasets show that the proposed solution outperforms state-of-the-art methods in zero-shot OOD detection task, while maintaining a competitive performance on ID classification task.

In multi-party chat, it is common for multiple conversations to occur concurrently, leading to intermingled conversation threads in chat logs. In this work, we propose a novel Context-Aware Thread Detection (CATD) model that automatically disentangles these conversation threads. We evaluate our model on four real-world datasets and demonstrate an overall im-provement in thread detection accuracy over state-of-the-art benchmarks.

Answer selection is a core component in any question-answering systems. It aims to select correct answer sentences for a given question from a pool of candidate sentences. In recent years, many deep learning methods have been proposed and shown excellent results for this task. However, these methods typically require extensive parameter (and hyper-parameter) tuning, which give rise to efficiency issues for large-scale datasets, and potentially make them less portable across new datasets and domains (as re-tuning is usually required). In this paper, we propose an extremely efficient hybrid model (FastHybrid) that tackles the problem from both an accuracy and scalability point of view. FastHybrid is a light-weight model that requires little tuning and adaptation across different domains. It combines a fast deep model (which will be introduced in the method section) with an initial information retrieval model to effectively and efficiently handle answer selection. We introduce a new efficient attention mechanism in the hybrid model and demonstrate its effectiveness on several QA datasets. Experimental results show that although the hybrid uses no training data, its accuracy is often on-par with supervised deep learning techniques, while significantly reducing training and tuning costs across different domains.