Naoki Otani

24 papers A* 4B 2Journal 9Unranked 8
YearRankTypeTitle / Venue / Authors
2026 conf
EACL (Volume 1: Long Papers)
Ryo Nagata, Daichi Mochihashi, Misato Ido, Yusuke Kubota, Naoki Otani, Yoshifumi Kawasaki, Hiroya Takamura
2025 conf
NAACL (Industry Track)
Naoki Otani, Nikita Bhutani, Estevam Hruschka
2024 conf
LREC/COLING
Ryo Nagata, Yoshifumi Kawasaki, Naoki Otani, Hiroya Takamura
2024 J jnl
CoRR
Naoki Otani, Nikita Bhutani, Estevam Hruschka
2024 J jnl
J. Nat. Lang. Process.
Ryo Nagata, Naoki Otani, Yoshifumi Kawasaki, Hiroya Takamura
2024 J jnl
CoRR
Haibo Sun, Naoki Otani, Hannah Kim, Dan Zhang, Nikita Bhutani
2023 conf
ACL (1)
Naoki Otani, Jun Araki, HyeongSik Kim, Eduard H. Hovy
2023 J jnl
CoRR
Leonie Weissweiler, Taiqi He, Naoki Otani, David R. Mortensen, Lori S. Levin, Hinrich Schütze
2023 J jnl
CoRR
Ryo Nagata, Hiroya Takamura, Naoki Otani, Yoshifumi Kawasaki
2023
Naoki Otani
2023 A* conf
EMNLP
Ryo Nagata, Hiroya Takamura, Naoki Otani, Yoshifumi Kawasaki
2022 conf
NAACL-HLT
Naoki Otani, Michael Gamon, Sujay Kumar Jauhar, Mei Yang, Sri Raghu Malireddi, Oriana Riva
2020 J jnl
CoRR
Lane Schwartz, Francis M. Tyers, Lori S. Levin, Christo Kirov, Patrick Littell, Chi-kiu Lo, Emily Prud'hommeaux, Hyunji Hayley Park, Kenneth Steimel, Rebecca Knowles, Jeffrey Micher, Lonny Strunk, Han Liu, Coleman Haley, Katherine J. Zhang, Robbie Jimerson, Vasilisa Andriyanets, Aldrian Obaja Muis, Naoki Otani, Jong Hyuk (Jay) Park, Zhisong Zhang
2020 conf
EMNLP (1)
Naoki Otani, Satoru Ozaki, Xingyuan Zhao, Yucen Li, Micaelah St Johns, Lori S. Levin
2019 J jnl
CoRR
Aditi Chaudhary, Siddharth Dalmia, Junjie Hu, Xinjian Li, Austin Matthews, Aldrian Obaja Muis, Naoki Otani, Shruti Rijhwani, Zaid Sheikh, Nidhi Vyas, Xinyi Wang, Jiateng Xie, Ruochen Xu, Chunting Zhou, Peter J. Jansen, Yiming Yang, Lori S. Levin, Florian Metze, Teruko Mitamura, David R. Mortensen, Graham Neubig, Eduard H. Hovy, Alan W. Black, Jaime G. Carbonell, Graham Horwood, Shabnam Tafreshi, Mona T. Diab, Efsun Sarioglu Kayi, Noura Farra, Kathleen R. McKeown
2019 conf
ACL (1)
Naoki Otani, Eduard H. Hovy
2019 conf
W-NUT@EMNLP
Shirley Anugrah Hayati, Aditi Chaudhary, Naoki Otani, Alan W. Black
2018 B conf
COLING
Naoki Otani, Hirokazu Kiyomaru, Daisuke Kawahara, Sadao Kurohashi
2018 B conf
COLING
Aldrian Obaja Muis, Naoki Otani, Nidhi Vyas, Ruochen Xu, Yiming Yang, Teruko Mitamura, Eduard H. Hovy
2018 A* conf
EMNLP
Ruochen Xu, Yiming Yang, Naoki Otani, Yuexin Wu
2018 J jnl
CoRR
Ruochen Xu, Yiming Yang, Naoki Otani, Yuexin Wu
2016 A* conf
EMNLP
Naoki Otani, Toshiaki Nakazawa, Daisuke Kawahara, Sadao Kurohashi
2016 J jnl
Expert Syst. Appl.
Naoki Otani, Yukino Baba, Hisashi Kashima
2015 A* conf
ICDM
Naoki Otani, Yukino Baba, Hisashi Kashima
tests/unit/conftest_binja_stubs.py
← Index tests/unit/conftest_binja_stubs.py python
"""Stubs for binaryninja module so decompiler unit tests can import
without a Binary Ninja license."""

import sys
from unittest.mock import MagicMock
from enum import IntEnum


# Stub binaryninja.enums
class BranchType(IntEnum):
    UnconditionalBranch = 0
    FalseBranch = 1
    TrueBranch = 2
    CallDestination = 3
    FunctionReturn = 4
    SystemCall = 5
    IndirectBranch = 6
    ExceptionBranch = 7
    UnresolvedBranch = 8
    UserDefinedBranch = 9


class InstructionTextTokenType(IntEnum):
    TextToken = 0
    InstructionToken = 1
    RegisterToken = 2
    IntegerToken = 3
    PossibleAddressToken = 4
    BeginMemoryOperandToken = 10
    EndMemoryOperandToken = 11
    FloatingPointToken = 12
    AnnotationToken = 13
    CodeRelativeAddressToken = 14
    ArgumentNameToken = 15
    HexDumpByteValueToken = 16
    HexDumpSkippedByteToken = 17
    HexDumpInvalidByteToken = 18
    HexDumpTextToken = 19
    OpcodeToken = 20
    StringToken = 21
    CharacterConstantToken = 22
    KeywordToken = 23
    TypeNameToken = 24
    FieldNameToken = 25
    NameSpaceToken = 26
    NameSpaceSeparatorToken = 27
    TagToken = 28
    StructOffsetToken = 29
    StructOffsetByteValueToken = 30
    StructureHexDumpTextToken = 31
    GotoLabelToken = 32
    CommentToken = 33
    PossibleValueToken = 34
    PossibleValueTypeToken = 35
    ArrayIndexToken = 36
    IndentationToken = 37
    UnknownMemoryToken = 38
    EnumerationMemberToken = 39
    OperationToken = 40
    BaseStructureOffsetToken = 41
    BaseStructureSeparatorToken = 42
    BraceToken = 43
    PlainTextToken = 44
    CollapsedInformationToken = 45


class SymbolType(IntEnum):
    FunctionSymbol = 0
    ImportAddressSymbol = 1
    ImportedFunctionSymbol = 2
    DataSymbol = 3
    ImportedDataSymbol = 4
    ExternalSymbol = 5
    LibraryFunctionSymbol = 6
    SymbolicFunctionSymbol = 7
    LocalLabelSymbol = 8


class HighLevelILOperation(IntEnum):
    HLIL_NOP = 0
    HLIL_ADD = 1
    HLIL_SUB = 2
    HLIL_MUL = 3
    HLIL_DIVS = 4
    HLIL_NEG = 5
    HLIL_NOT = 6
    HLIL_AND = 7
    HLIL_OR = 8
    HLIL_XOR = 9
    HLIL_LSR = 10
    HLIL_LSL = 11
    HLIL_MODS = 12
    HLIL_IF = 13
    HLIL_GOTO = 14
    HLIL_RET = 15
    HLIL_ASSIGN = 16
    HLIL_CALL = 17
    HLIL_VAR = 18
    HLIL_CONST = 19
    HLIL_BLOCK = 20


class LowLevelILOperation(IntEnum):
    LLIL_NOP = 0
    LLIL_SET_REG = 1
    LLIL_SET_REG_SPLIT = 2
    LLIL_SET_FLAG = 3
    LLIL_LOAD = 4
    LLIL_STORE = 5
    LLIL_PUSH = 6
    LLIL_POP = 7
    LLIL_REG = 8
    LLIL_CONST = 9
    LLIL_CONST_PTR = 10
    LLIL_FLAG = 11
    LLIL_FLAG_BIT = 12
    LLIL_ADD = 13
    LLIL_ADC = 14
    LLIL_SUB = 15
    LLIL_SBB = 16
    LLIL_AND = 17
    LLIL_OR = 18
    LLIL_XOR = 19
    LLIL_LSL = 20
    LLIL_LSR = 21
    LLIL_ASR = 22
    LLIL_ROL = 23
    LLIL_RLC = 24
    LLIL_ROR = 25
    LLIL_RRC = 26
    LLIL_MUL = 27
    LLIL_MULU_DP = 28
    LLIL_MULS_DP = 29
    LLIL_DIVU = 30
    LLIL_DIVU_DP = 31
    LLIL_DIVS = 32
    LLIL_DIVS_DP = 33
    LLIL_MODU = 34
    LLIL_MODS = 35
    LLIL_NEG = 36
    LLIL_NOT = 37
    LLIL_SX = 38
    LLIL_ZX = 39
    LLIL_LOW_PART = 40
    LLIL_JUMP = 41
    LLIL_JUMP_TO = 42
    LLIL_CALL = 43
    LLIL_CALL_SSA = 44
    LLIL_RET = 45
    LLIL_NORET = 46
    LLIL_IF = 47
    LLIL_GOTO = 48
    LLIL_FLAG_COND = 49
    LLIL_CMP_E = 50
    LLIL_CMP_NE = 51
    LLIL_CMP_SLT = 52
    LLIL_CMP_ULT = 53
    LLIL_CMP_SLE = 54
    LLIL_CMP_ULE = 55
    LLIL_CMP_SGE = 56
    LLIL_CMP_UGE = 57
    LLIL_CMP_SGT = 58
    LLIL_CMP_UGT = 59
    LLIL_TEST_BIT = 60
    LLIL_BOOL_TO_INT = 61
    LLIL_TAILCALL = 62
    LLIL_SYSCALL = 63
    LLIL_BP = 64
    LLIL_TRAP = 65
    LLIL_UNDEF = 66
    LLIL_UNIMPL = 67
    LLIL_UNIMPL_MEM = 68


class AnalysisState(IntEnum):
    IdleState = 0
    DisassembleState = 1
    AnalyzeState = 2


def install_binja_stubs():
    """Install binaryninja module stubs into sys.modules.
    Call this BEFORE importing any decompiler modules.
    Idempotent — returns the existing mock if already installed.
    """
    if "binaryninja" in sys.modules and not isinstance(sys.modules["binaryninja"], MagicMock):
        return sys.modules["binaryninja"]
    if "binaryninja" in sys.modules and hasattr(sys.modules["binaryninja"], "_redb_stub"):
        return sys.modules["binaryninja"]

    # Create the main mock
    bn_mock = MagicMock()
    bn_mock._redb_stub = True

    # Wire up enums as real enums (not mocks)
    enums_mod = MagicMock()
    enums_mod.BranchType = BranchType
    enums_mod.InstructionTextTokenType = InstructionTextTokenType
    enums_mod.SymbolType = SymbolType
    enums_mod.HighLevelILOperation = HighLevelILOperation
    enums_mod.LowLevelILOperation = LowLevelILOperation
    enums_mod.AnalysisState = AnalysisState

    bn_mock.enums = enums_mod
    bn_mock.enums.BranchType = BranchType
    bn_mock.enums.InstructionTextTokenType = InstructionTextTokenType
    bn_mock.enums.SymbolType = SymbolType
    bn_mock.enums.HighLevelILOperation = HighLevelILOperation
    bn_mock.enums.LowLevelILOperation = LowLevelILOperation
    bn_mock.enums.AnalysisState = AnalysisState

    # LowLevelILOperation on the top-level module
    bn_mock.LowLevelILOperation = LowLevelILOperation
    bn_mock.LowLevelILInstruction = MagicMock

    # highlevelil sub-module
    hlil_mod = MagicMock()
    hlil_mod.HighLevelILInstruction = type("HighLevelILInstruction", (), {})
    bn_mock.highlevelil = hlil_mod

    # lowlevelil sub-module
    llil_mod = MagicMock()
    llil_mod.LowLevelILAdd = type("LowLevelILAdd", (), {})
    llil_mod.LowLevelILConst = type("LowLevelILConst", (), {})
    llil_mod.LowLevelILConstPtr = type("LowLevelILConstPtr", (), {})
    llil_mod.LowLevelILLoad = type("LowLevelILLoad", (), {})
    llil_mod.LowLevelILLsl = type("LowLevelILLsl", (), {})
    llil_mod.LowLevelILMul = type("LowLevelILMul", (), {})
    llil_mod.LowLevelILPop = type("LowLevelILPop", (), {})
    llil_mod.LowLevelILPush = type("LowLevelILPush", (), {})
    llil_mod.LowLevelILReg = type("LowLevelILReg", (), {})
    llil_mod.LowLevelILStore = type("LowLevelILStore", (), {})
    llil_mod.LowLevelILSub = type("LowLevelILSub", (), {})
    bn_mock.lowlevelil = llil_mod

    # mediumlevelil sub-module
    mlil_mod = MagicMock()
    mlil_mod.MediumLevelILConst = type("MediumLevelILConst", (), {})
    mlil_mod.MediumLevelILConstPtr = type("MediumLevelILConstPtr", (), {})
    bn_mock.mediumlevelil = mlil_mod

    sys.modules["binaryninja"] = bn_mock
    sys.modules["binaryninja.enums"] = enums_mod
    sys.modules["binaryninja.lowlevelil"] = llil_mod
    sys.modules["binaryninja.highlevelil"] = hlil_mod
    sys.modules["binaryninja.mediumlevelil"] = mlil_mod

    return bn_mock


# ============================================================================
# Mock Factories
# ============================================================================

class MockToken:
    """Mock for instruction text tokens."""
    def __init__(self, text, token_type=None):
        self.text = text
        if token_type is None:
            self.type = InstructionTextTokenType.TextToken
        else:
            self.type = token_type

    def __str__(self):
        return self.text


class MockDisassemblyLine:
    """Mock for a disassembly text line."""
    def __init__(self, tokens=None):
        self.tokens = tokens or []

    def __str__(self):
        return "".join(t.text for t in self.tokens)


class MockEdge:
    """Mock for a basic block edge."""
    def __init__(self, source=None, target=None, edge_type=None):
        self.source = source
        self.target = target
        self.type = edge_type


class MockBasicBlock:
    """Mock for a basic block."""
    def __init__(
        self,
        start=0,
        end=0,
        disassembly_text=None,
        outgoing_edges=None,
        incoming_edges=None,
        dominators=None,
        post_dominators=None,
        dominance_frontier=None,
        dominator_tree_children=None,
        instruction_count=None,
    ):
        self.start = start
        self.end = end
        self.disassembly_text = disassembly_text or []
        self.outgoing_edges = outgoing_edges or []
        self.incoming_edges = incoming_edges or []
        self.dominators = dominators if dominators is not None else [self]
        self.post_dominators = post_dominators if post_dominators is not None else [self]
        self.dominance_frontier = dominance_frontier if dominance_frontier is not None else set()
        self.dominator_tree_children = dominator_tree_children or []
        self.instruction_count = instruction_count if instruction_count is not None else len(self.disassembly_text)

    def __iter__(self):
        return iter(self.disassembly_text)


class MockFunction:
    """Mock for a Binary Ninja function."""
    def __init__(
        self,
        name="sub_1000",
        start=0x1000,
        basic_blocks=None,
        instructions=None,
        hlil=None,
        llil=None,
        mlil=None,
        symbol=None,
        is_thunk=False,
        stack_adjustment=0,
        call_sites=None,
        caller_sites=None,
        low_level_il=None,
    ):
        self.name = name
        self.start = start
        self.basic_blocks = basic_blocks or []
        self._instructions = instructions or []
        self.hlil = hlil
        self.llil = llil
        self.mlil = mlil
        self.symbol = symbol
        self.is_thunk = is_thunk
        self.stack_adjustment = stack_adjustment
        self.call_sites = call_sites or []
        self.caller_sites = caller_sites or []
        self.low_level_il = low_level_il

    @property
    def instructions(self):
        return iter(self._instructions)

    def get_basic_block_at(self, addr):
        for bb in self.basic_blocks:
            if bb.start <= addr < bb.end or bb.start == addr:
                return bb
        return self.basic_blocks[0] if self.basic_blocks else None

    def get_regs_read_by(self, addr, arch):
        return []

    def get_regs_written_by(self, addr, arch):
        return []

    def __str__(self):
        return f"uint64_t {self.name}()"


class MockBinaryView:
    """Mock for a Binary Ninja binary view."""
    def __init__(
        self,
        functions=None,
        strings=None,
        arch=None,
    ):
        self.functions = functions or []
        self.strings = strings or []
        self.arch = arch

    def get_segment_at(self, addr):
        return None

    def get_section_at(self, addr):
        return None

    def get_symbol_at(self, addr):
        return None

    def get_functions_at(self, addr):
        return []

    def get_string_at(self, addr):
        return None

    def get_data_var_at(self, addr):
        return None


class MockSymbol:
    """Mock for a Binary Ninja symbol."""
    def __init__(self, symbol_type=None, name="unknown"):
        self.type = symbol_type if symbol_type is not None else SymbolType.FunctionSymbol
        self.name = name
        self.full_name = name


class MockILInstruction:
    """Mock for an IL instruction (LLIL/HLIL)."""
    def __init__(self, operation, operands=None, address=0):
        self.operation = operation
        self.operands = operands or []
        self.address = address


class MockStringEntry:
    """Mock for a Binary Ninja string reference."""
    def __init__(self, value, raw=None, start=0, length=0, string_type=None):
        self.value = value
        self.raw = raw if raw is not None else value.encode("utf-8") if isinstance(value, str) else value
        self.start = start
        self.length = length if length else len(self.raw)
        self.type = string_type or MockStringType("Utf8String")


class MockStringType:
    """Mock for string type."""
    def __init__(self, name="Utf8String"):
        self.name = name