A long-term goal of machine learning research is to build an intelligent dialog agent. Most research in natural language understanding has focused on learning from fixed training sets of labeled data, with supervision either at the word level (tagging, parsing tasks) or sentence level (question answering, machine translation). This kind of supervision is not realistic of how humans learn, where language is both learned by, and used for, communication. In this work, we study dialog-based language learning, where supervision is given naturally and implicitly in the response of the dialog partner during the conversation. We study this setup in two domains: the bAbI dataset of [23] and large-scale question answering from [3]. We evaluate a set of baseline learning strategies on these tasks, and show that a novel model incorporating predictive lookahead is a promising approach for learning from a teacher's response. In particular, a surprising result is that it can learn to answer questions correctly without any reward-based supervision at all.

Unsupervised semantic segmentation aims to discover groupings within images, capturing objects' view-invariance without external supervision. Moreover, this task is inherently ambiguous due to the varying levels of semantic granularity. Existing methods often bypass this ambiguity using dataset-specific priors. In our research, we address this ambiguity head-on and provide a universal tool for pixel-level semantic parsing of images guided by the latent representations encoded in self-supervised models. We introduce a novel algebraic approach that recursively decomposes an image into nested subgraphs, dynamically estimating their count and ensuring clear separation.The innovative approach identifies scene-specific primitives and constructs a hierarchy-agnostic tree of semantic regions from the image pixels.

Practical semantic parsers are expected to understand user utterances and map them to executable programs, even when these are ambiguous. We introduce a new benchmark, AMBROSIA, which we hope will inform and inspire the development of text-to-SQL parsers capable of recognizing and interpreting ambiguous requests. Our dataset contains questions showcasing three different types of ambiguity (scope ambiguity, attachment ambiguity, and vagueness), their interpretations, and corresponding SQL queries. In each case, the ambiguity persists even when the database context is provided. This is achieved through a novel approach that involves controlled generation of databases from scratch. We benchmark various LLMs on AMBROSIA, revealing that even the most advanced models struggle to identify and interpret ambiguity in questions.

How much data is required to learn the structure of a language via next-token prediction? We study this question for synthetic datasets generated via a Probabilistic Context-Free Grammar (PCFG)---a hierarchical generative model that captures the tree-like structure of natural languages. We determine token-token correlations analytically in our model and show that they can be used to build a representation of the grammar's hidden variables, the longer the range the deeper the variable. In addition, a finite training set limits the resolution of correlations to an effective range, whose size grows with that of the training set. As a result, a Language Model trained with increasingly many examples can build a deeper representation of the grammar's structure, thus reaching good performance despite the high dimensionality of the problem. We conjecture that the relationship between training set size and effective range of correlations holds beyond our synthetic datasets, and we test it in a collection of lines from Shakespeare's plays. In particular, we show that reducing the input size leads to saturation of the test loss decay at a characteristic training set size that can be predicted in our framework.

In this paper, we introduce the first learning-free model reuse task within the non-Euclidean domain, termed as Deep Graph Mating (Grama). We strive to create a child Graph Neural Network (GNN) that integrates knowledge from pre-trained parent models without requiring re-training, fine-tuning, or annotated labels. To this end, we begin by investigating the permutation invariance property of GNNs, which leads us to develop two vanilla approaches for Grama: Vanilla Parameter Interpolation (VPI) and Vanilla Alignment Prior to Interpolation (VAPI), both employing topology-independent interpolation in the parameter space. However, neither approach has achieved the anticipated results. Through theoretical analysis of VPI and VAPI, we identify critical challenges unique to Grama, including increased sensitivity to parameter misalignment and further the inherent topology-dependent complexities. Motivated by these findings, we propose the Dual-Message Coordination and Calibration (DuMCC) methodology, comprising the Parent Message Coordination (PMC) scheme to optimise the permutation matrices for parameter interpolation by coordinating aggregated messages, and the Child Message Calibration (CMC) scheme to mitigate over-smoothing identified in PMC by calibrating the message statistics within child GNNs. Experiments across diverse domains, including node and graph property prediction, 3D object recognition, and large-scale semantic parsing, demonstrate that the proposed DuMCC effectively enables training-free knowledge transfer, yielding results on par with those of pre-trained models.

We present Memory Augmented Policy Optimization (MAPO), a simple and novel way to leverage a memory buffer of promising trajectories to reduce the variance of policy gradient estimate. MAPO is applicable to deterministic environments with discrete actions, such as structured prediction and combinatorial optimization tasks. We express the expected return objective as a weighted sum of two terms: an expectation over the high-reward trajectories inside the memory buffer, and a separate expectation over trajectories outside the buffer. To make an efficient algorithm of MAPO, we propose: (1) memory weight clipping to accelerate and stabilize training; (2) systematic exploration to discover high-reward trajectories; (3) distributed sampling from inside and outside of the memory buffer to scale up training. MAPO improves the sample efficiency and robustness of policy gradient, especially on tasks with sparse rewards. We evaluate MAPO on weakly supervised program synthesis from natural language (semantic parsing). On the WikiTableQuestions benchmark, we improve the state-of-the-art by 2.6%, achieving an accuracy of 46.3%. On the WikiSQL benchmark, MAPO achieves an accuracy of 74.9% with only weak supervision, outperforming several strong baselines with full supervision. Our source code is available at https://goo.gl/TXBp4e

We present an approach to map utterances in conversation to logical forms, which will be executed on a large-scale knowledge base. To handle enormous ellipsis phenomena in conversation, we introduce dialog memory management to manipulate historical entities, predicates, and logical forms when inferring the logical form of current utterances. Dialog memory management is embodied in a generative model, in which a logical form is interpreted in a top-down manner following a small and flexible grammar. We learn the model from denotations without explicit annotation of logical forms, and evaluate it on a large-scale dataset consisting of 200K dialogs over 12.8M entities. Results verify the benefits of modeling dialog memory, and show that our semantic parsing-based approach outperforms a memory network based encoder-decoder model by a huge margin.

We present an approach to map utterances in conversation to logical forms, which will be executed on a large-scale knowledge base. To handle enormous ellipsis phenomena in conversation, we introduce dialog memory management to manipulate historical entities, predicates, and logical forms when inferring the logical form of current utterances. Dialog memory management is embodied in a generative model, in which a logical form is interpreted in a top-down manner following a small and flexible grammar. We learn the model from denotations without explicit annotation of logical forms, and evaluate it on a large-scale dataset consisting of 200K dialogs over 12.8M entities. Results verify the benefits of modeling dialog memory, and show that our semantic parsing-based approach outperforms a memory network based encoder-decoder model by a huge margin.

Human scene understanding uses a variety of visual and non-visual cues to perform inference on object types, poses, and relations. Physics is a rich and universal cue that we exploit to enhance scene understanding. In this paper, we integrate the physical cue of stability into the learning process by looping in a physics engine into bottom-up recognition models, and apply it to the problem of 3D scene parsing. We first show that applying physics supervision to an existing scene understanding model increases performance, produces more stable predictions, and allows training to an equivalent performance level with fewer annotated training examples. We then present a novel architecture for 3D scene parsing named Prim R-CNN, learning to predict bounding boxes as well as their 3D size, translation, and rotation. With physics supervision, Prim R-CNN outperforms existing scene understanding approaches on this problem. Finally, we show that finetuning with physics supervision on unlabeled real images improves real domain transfer of models training on synthetic data.

Program synthesis of general-purpose source code from natural language specifi-cations is challenging due to the need to reason about high-level patterns in thetarget program and low-level implementation details at the same time.